test: preserve Dev verification contracts through Refactor APIs
This commit is contained in:
KOKO\Mimi
@@ -96,3 +96,19 @@ def test_p_style_002_msvc_targets_enable_standard_exception_unwinding():
|
||||
assert "/EHsc" in compile_options.group("body"), (
|
||||
f"{target} must enable standard C++ exception unwinding under MSVC"
|
||||
)
|
||||
|
||||
|
||||
# The maintained solution uses the shared native property sheet; both paths
|
||||
# must keep standard exception unwinding. Doxygen remains optional above.
|
||||
import xml.etree.ElementTree as ET
|
||||
|
||||
ns = {"m": "http://schemas.microsoft.com/developer/msbuild/2003"}
|
||||
props = ET.parse(ROOT / "msvc" / "Fesa.Common.props")
|
||||
assert props.findtext(".//m:ExceptionHandling", namespaces=ns) == "Sync"
|
||||
for target in ("fesa_solver", "fesa_cli", "fesa_unit_tests",
|
||||
"fesa_integration_tests", "fesa_reference_tests"):
|
||||
project = ET.parse(ROOT / "msvc" / f"{target}.vcxproj")
|
||||
imports = [item.attrib.get("Project") for item in project.findall("m:Import", ns)]
|
||||
assert "Fesa.Common.props" in imports, target
|
||||
overrides = project.findall(".//m:ExceptionHandling", ns)
|
||||
assert all(item.text == "Sync" for item in overrides), target
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
#include <limits>
|
||||
#include "analysis/eigen_reduction.h"
|
||||
|
||||
#include <gtest/gtest.h>
|
||||
@@ -46,6 +47,37 @@ fesa::ShellNodeInitialFrame TiltedFrame() {
|
||||
return {0U, {0.6, 0.0, 0.8}, {0.0, 1.0, 0.0}, {-0.8, 0.0, 0.6}};
|
||||
}
|
||||
|
||||
TEST(EigenReduction, RejectsNonfiniteUsedBasisAndPreservesPriorCandidate) {
|
||||
const fesa::ShellNodeInitialFrame frame{0U, {0, 0, 1}, {1, 0, 0}, {0, 1, 0}};
|
||||
const auto mass = NodalMass(frame.director);
|
||||
fesa::Matrix stiffness(6U, 6U);
|
||||
for (std::size_t i = 0; i < 5U; ++i) stiffness(i, i) = mass(i, i) * 7.0;
|
||||
stiffness(5U, 5U) = .25;
|
||||
const auto matrix = Sparse(stiffness);
|
||||
const std::vector<std::uint8_t> mask(6U, 0U);
|
||||
const auto prior = fesa::eigen_internal::BuildEigenReduction(
|
||||
matrix, {mass}, {frame}, mask, {.25}, 2.0);
|
||||
ASSERT_TRUE(prior.HasValue());
|
||||
const auto prior_values = prior.Value().whitened_operator.Values();
|
||||
for (const double invalid : {std::numeric_limits<double>::quiet_NaN(),
|
||||
std::numeric_limits<double>::infinity()}) {
|
||||
for (const bool first_tangent : {false, true}) {
|
||||
auto bad_frame = frame;
|
||||
(first_tangent ? bad_frame.tangent_a : bad_frame.tangent_b)[0] = invalid;
|
||||
const auto rejected = fesa::eigen_internal::BuildEigenReduction(
|
||||
matrix, {mass}, {bad_frame}, mask, {.25}, 2.0);
|
||||
ASSERT_FALSE(rejected.HasValue());
|
||||
EXPECT_EQ(rejected.GetStatus().Category(), fesa::FailureCategory::kSolver);
|
||||
EXPECT_EQ(rejected.GetStatus().Diagnostics()[0].code,
|
||||
"invalid-eigen-mass-space");
|
||||
EXPECT_EQ(prior.Value().whitened_operator.Values(), prior_values);
|
||||
}
|
||||
}
|
||||
const auto rerun = fesa::eigen_internal::BuildEigenReduction(
|
||||
matrix, {mass}, {frame}, mask, {.25}, 2.0);
|
||||
ASSERT_TRUE(rerun.HasValue());
|
||||
EXPECT_EQ(rerun.Value().whitened_operator.Values(), prior_values);
|
||||
}
|
||||
} // namespace
|
||||
|
||||
TEST(EigenReduction, KeepsPositivePartialGlobalRotationAndOriginalPencil) {
|
||||
|
||||
@@ -5,6 +5,8 @@
|
||||
#include <cmath>
|
||||
#include <cfenv>
|
||||
#include <cstddef>
|
||||
#include <cstring>
|
||||
#include <functional>
|
||||
#include <iostream>
|
||||
#include <memory>
|
||||
#include <limits>
|
||||
@@ -19,6 +21,7 @@
|
||||
#endif
|
||||
|
||||
#include "analysis/hht_reduced_internal.h"
|
||||
#include "math/dense_blas_internal.h"
|
||||
#include "fesa/analysis/analysis_model.h"
|
||||
#include "fesa/analysis/hht_time_integration.h"
|
||||
#include "fesa/assembly/parallel_for.h"
|
||||
@@ -26,6 +29,71 @@
|
||||
|
||||
namespace {
|
||||
|
||||
class RestoreTrialEnvironment {
|
||||
public:
|
||||
RestoreTrialEnvironment()
|
||||
: rounding_(std::fegetround()),
|
||||
dynamic_(mkl_get_dynamic()),
|
||||
tls_(mkl_set_num_threads_local(0)) {
|
||||
#if defined(_M_X64)
|
||||
mxcsr_ = _mm_getcsr();
|
||||
_mm_setcsr((_mm_getcsr() | 0x1F80U) & ~0x8040U);
|
||||
#endif
|
||||
static_cast<void>(std::fesetround(FE_TONEAREST));
|
||||
mkl_set_dynamic(0);
|
||||
}
|
||||
~RestoreTrialEnvironment() {
|
||||
mkl_set_dynamic(dynamic_);
|
||||
static_cast<void>(mkl_set_num_threads_local(tls_));
|
||||
static_cast<void>(std::fesetround(rounding_));
|
||||
#if defined(_M_X64)
|
||||
_mm_setcsr(mxcsr_);
|
||||
#endif
|
||||
}
|
||||
|
||||
private:
|
||||
int rounding_;
|
||||
int dynamic_;
|
||||
int tls_;
|
||||
#if defined(_M_X64)
|
||||
unsigned int mxcsr_;
|
||||
#endif
|
||||
};
|
||||
|
||||
void ExpectSameBits(const double left, const double right) {
|
||||
EXPECT_EQ(std::memcmp(&left, &right, sizeof(double)), 0);
|
||||
}
|
||||
|
||||
void ExpectSameOperators(
|
||||
const fesa::hht_reduced_internal::ConstraintOperators& left,
|
||||
const fesa::hht_reduced_internal::ConstraintOperators& right) {
|
||||
ASSERT_EQ(left.rows.size(), right.rows.size());
|
||||
for (std::size_t row = 0U; row < left.rows.size(); ++row) {
|
||||
const auto& a = left.rows[row];
|
||||
const auto& b = right.rows[row];
|
||||
ExpectSameBits(a.value, b.value);
|
||||
ExpectSameBits(a.value_scale, b.value_scale);
|
||||
ExpectSameBits(a.time_first, b.time_first);
|
||||
ExpectSameBits(a.time_second, b.time_second);
|
||||
for (const auto& pair : {std::make_pair(&a.gradient, &b.gradient),
|
||||
std::make_pair(&a.time_gradient, &b.time_gradient),
|
||||
std::make_pair(&a.third_directional_gradient,
|
||||
&b.third_directional_gradient)}) {
|
||||
ASSERT_EQ(pair.first->size(), pair.second->size());
|
||||
for (std::size_t i = 0U; i < pair.first->size(); ++i) {
|
||||
EXPECT_EQ((*pair.first)[i].dof, (*pair.second)[i].dof);
|
||||
ExpectSameBits((*pair.first)[i].value, (*pair.second)[i].value);
|
||||
}
|
||||
}
|
||||
ASSERT_EQ(a.hessian.size(), b.hessian.size());
|
||||
for (std::size_t i = 0U; i < a.hessian.size(); ++i) {
|
||||
EXPECT_EQ(a.hessian[i].row, b.hessian[i].row);
|
||||
EXPECT_EQ(a.hessian[i].column, b.hessian[i].column);
|
||||
ExpectSameBits(a.hessian[i].value, b.hessian[i].value);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
struct Fixture {
|
||||
std::unique_ptr<fesa::Domain> domain;
|
||||
fesa::DofManager dofs;
|
||||
@@ -394,6 +462,479 @@ TEST(HhtReducedChart, InvertibleGraphDoesNotCertifySelectorTransversality) {
|
||||
assembly, chart.Value(), solver).HasValue());
|
||||
}
|
||||
|
||||
TEST(HhtReducedOperators,
|
||||
CompleteTrialConstraintDataMatchesFreshAndOwnsCopies) {
|
||||
RestoreTrialEnvironment restore;
|
||||
const auto fixture = MakeFixture(false, true);
|
||||
const auto shells =
|
||||
fesa::hht_internal::BuildRuntimeShells(*fixture.domain, fixture.dofs);
|
||||
ASSERT_TRUE(shells.HasValue());
|
||||
const fesa::Vector zero(fixture.dofs.FullDofCount());
|
||||
auto q = zero;
|
||||
auto v = zero;
|
||||
auto force = zero;
|
||||
auto rate = zero;
|
||||
auto acceleration = zero;
|
||||
for (std::size_t i = 0U; i < zero.Size(); ++i) {
|
||||
q[i] = 0.001 * static_cast<double>((i % 5U) + 1U);
|
||||
v[i] = 0.002 * static_cast<double>((i % 7U) + 1U);
|
||||
if (i % 6U >= 3U) {
|
||||
force[i] = 0.03;
|
||||
rate[i] = -0.02;
|
||||
acceleration[i] = 0.01;
|
||||
}
|
||||
}
|
||||
auto assembled = Assemble(fixture, shells.Value(), q, v, zero, force, true);
|
||||
ASSERT_TRUE(assembled.HasValue());
|
||||
ASSERT_TRUE(assembled.Value().trial_constraints.has_value());
|
||||
ASSERT_EQ(assembled.Value().trial_constraints->shells.size(),
|
||||
shells.Value().size());
|
||||
const auto chart = fesa::hht_reduced_internal::BuildFixedChart(
|
||||
fixture.dofs, assembled.Value().rotations);
|
||||
ASSERT_TRUE(chart.HasValue());
|
||||
for (std::size_t e = 0U; e < shells.Value().size(); ++e) {
|
||||
const auto& saved = assembled.Value().trial_constraints->shells[e];
|
||||
ASSERT_TRUE(saved.directional_internal);
|
||||
fesa::NonlinearMitc4TrialDofs trial{};
|
||||
fesa::Vector direction{24U};
|
||||
for (std::size_t node = 0U; node < 4U; ++node) {
|
||||
const auto first = 6U * node;
|
||||
trial.displacement[node] =
|
||||
fesa::Vector3{saved.q[first], saved.q[first + 1U], saved.q[first + 2U]};
|
||||
trial.rotation_vector[node] = fesa::Vector3{
|
||||
saved.q[first + 3U], saved.q[first + 4U], saved.q[first + 5U]};
|
||||
}
|
||||
for (std::size_t i = 0U; i < 24U; ++i) direction[i] = saved.v[i];
|
||||
const auto response = shells.Value()[e].internal->EvaluateTrial(trial, &direction);
|
||||
ASSERT_TRUE(response.HasValue());
|
||||
for (std::size_t node = 0U; node < 4U; ++node) {
|
||||
ExpectSameBits(saved.drilling_constraint[node],
|
||||
response.Value().drilling_constraint[node]);
|
||||
for (std::size_t i = 0U; i < 24U; ++i) {
|
||||
ExpectSameBits(saved.drilling_constraint_gradient(node, i),
|
||||
response.Value().drilling_constraint_gradient(node, i));
|
||||
ExpectSameBits(
|
||||
saved.drilling_constraint_third_directional_gradient[node][i],
|
||||
response.Value()
|
||||
.drilling_constraint_third_directional_gradient[node][i]);
|
||||
for (std::size_t j = 0U; j < 24U; ++j)
|
||||
ExpectSameBits(
|
||||
saved.drilling_constraint_hessian[node](i, j),
|
||||
response.Value().drilling_constraint_hessian[node](i, j));
|
||||
}
|
||||
}
|
||||
}
|
||||
const auto evaluate = [&](const fesa::hht_internal::DynamicAssembly& value) {
|
||||
return fesa::hht_reduced_internal::EvaluateConstraintOperators(
|
||||
*fixture.domain, fixture.dofs, shells.Value(), value, chart.Value(),
|
||||
rate, acceleration);
|
||||
};
|
||||
auto fresh = assembled.Value();
|
||||
fresh.trial_constraints.reset();
|
||||
const auto reference = evaluate(fresh);
|
||||
const auto reused = evaluate(assembled.Value());
|
||||
ASSERT_TRUE(reference.HasValue());
|
||||
ASSERT_TRUE(reused.HasValue());
|
||||
ExpectSameOperators(reused.Value(), reference.Value());
|
||||
auto copy = assembled.Value();
|
||||
copy.trial_constraints->shells[0U].drilling_constraint[0U] += 7.0;
|
||||
// Test-only finite marker proves the selected route actually reads its owner.
|
||||
const auto marker = evaluate(copy);
|
||||
ASSERT_TRUE(marker.HasValue());
|
||||
EXPECT_NE(marker.Value().rows[0U].value, reused.Value().rows[0U].value);
|
||||
EXPECT_NE(
|
||||
copy.trial_constraints->shells[0U].drilling_constraint[0U],
|
||||
assembled.Value().trial_constraints->shells[0U].drilling_constraint[0U]);
|
||||
auto moved = std::move(assembled.Value());
|
||||
const auto moved_result = evaluate(moved);
|
||||
ASSERT_TRUE(moved_result.HasValue());
|
||||
ExpectSameOperators(moved_result.Value(), reference.Value());
|
||||
fesa::DynamicAcceptedFrameState frame{};
|
||||
frame.generalized_coordinates = q;
|
||||
frame.velocity = v;
|
||||
frame.acceleration = zero;
|
||||
frame.algorithmic_acceleration = zero;
|
||||
frame.external_force = force;
|
||||
const auto parameters = fesa::MakeHhtParameters(-0.05);
|
||||
ASSERT_TRUE(parameters.HasValue());
|
||||
fesa::TbbParallelFor parallel;
|
||||
const auto tbb = fesa::hht_internal::EvaluateAssembly(
|
||||
*fixture.domain, fixture.dofs, shells.Value(), frame, zero, 0.1,
|
||||
parameters.Value(), parallel, true);
|
||||
ASSERT_TRUE(tbb.HasValue());
|
||||
const auto tbb_result = evaluate(tbb.Value());
|
||||
ASSERT_TRUE(tbb_result.HasValue());
|
||||
ExpectSameOperators(tbb_result.Value(), reference.Value());
|
||||
}
|
||||
|
||||
TEST(HhtReducedOperators,
|
||||
ChangedTrialConstraintContextFallsBackInOriginalPosition) {
|
||||
RestoreTrialEnvironment restore;
|
||||
const auto fixture = MakeFixture(false);
|
||||
const auto shells =
|
||||
fesa::hht_internal::BuildRuntimeShells(*fixture.domain, fixture.dofs);
|
||||
ASSERT_TRUE(shells.HasValue());
|
||||
const fesa::Vector zero(fixture.dofs.FullDofCount());
|
||||
const auto assembled =
|
||||
Assemble(fixture, shells.Value(), zero, zero, zero, zero, true);
|
||||
ASSERT_TRUE(assembled.HasValue());
|
||||
ASSERT_TRUE(assembled.Value().trial_constraints.has_value());
|
||||
ASSERT_TRUE(
|
||||
assembled.Value().trial_constraints->shells[0U].directional_internal);
|
||||
const auto chart = fesa::hht_reduced_internal::BuildFixedChart(
|
||||
fixture.dofs, assembled.Value().rotations);
|
||||
ASSERT_TRUE(chart.HasValue());
|
||||
const auto evaluate = [&](const fesa::hht_internal::DynamicAssembly& value) {
|
||||
return fesa::hht_reduced_internal::EvaluateConstraintOperators(
|
||||
*fixture.domain, fixture.dofs, shells.Value(), value, chart.Value(),
|
||||
zero, zero);
|
||||
};
|
||||
using Assembly = fesa::hht_internal::DynamicAssembly;
|
||||
std::vector<std::function<void(Assembly&)>> changes{
|
||||
[](Assembly& a) { a.frame.generalized_coordinates[2U] = 0.001; },
|
||||
[](Assembly& a) { a.frame.velocity[3U] = 0.003; },
|
||||
[](Assembly& a) { a.frame.time = 0.1; },
|
||||
[](Assembly& a) { ++a.frame.frame_index; },
|
||||
[](Assembly& a) { ++a.frame.increment_index; },
|
||||
[](Assembly& a) { ++a.frame.iteration_count; },
|
||||
[](Assembly& a) { a.frame.is_initial = true; },
|
||||
[](Assembly& a) { a.trial_constraints->source_path = "different.inp"; },
|
||||
[](Assembly& a) { ++a.trial_constraints->shells[0U].element_index; },
|
||||
[](Assembly& a) { ++a.trial_constraints->shells[0U].scatter[0U]; },
|
||||
[](Assembly& a) {
|
||||
a.trial_constraints->shells[0U].directional_internal = false;
|
||||
},
|
||||
[](Assembly& a) {
|
||||
a.trial_constraints->shells[0U].node_source_ids[0U].instance_name +=
|
||||
"x";
|
||||
},
|
||||
[](Assembly& a) {
|
||||
++a.trial_constraints->shells[0U].node_source_ids[0U].source_label;
|
||||
},
|
||||
[](Assembly& a) {
|
||||
a.trial_constraints->shells[0U].node_source_ids[0U].source_label_text +=
|
||||
"x";
|
||||
},
|
||||
[](Assembly& a) {
|
||||
++a.trial_constraints->shells[0U].configuration.source.line;
|
||||
},
|
||||
[](Assembly& a) {
|
||||
a.trial_constraints->shells[0U].configuration.source.file =
|
||||
"different.inp";
|
||||
},
|
||||
[](Assembly& a) {
|
||||
a.trial_constraints->shells[0U].configuration.identity += "x";
|
||||
},
|
||||
[](Assembly& a) { a.trial_constraints->shells[0U].q[0U] = -0.0; },
|
||||
[](Assembly& a) { a.trial_constraints->shells[0U].v[0U] = -0.0; },
|
||||
[](Assembly& a) {
|
||||
a.trial_constraints->shells[0U].drilling_constraint_gradient =
|
||||
fesa::Matrix{0U, 0U};
|
||||
},
|
||||
[](Assembly& a) {
|
||||
a.trial_constraints->shells[0U].drilling_constraint_hessian[2U] =
|
||||
fesa::Matrix{0U, 0U};
|
||||
},
|
||||
[](Assembly& a) {
|
||||
a.trial_constraints->shells[0U]
|
||||
.drilling_constraint_third_directional_gradient[1U] =
|
||||
fesa::Vector{0U};
|
||||
},
|
||||
[](Assembly& a) {
|
||||
a.trial_constraints->shells[0U].drilling_constraint_hessian[0U](
|
||||
0U, 0U) = std::numeric_limits<double>::infinity();
|
||||
},
|
||||
[](Assembly& a) {
|
||||
a.trial_constraints->shells[0U]
|
||||
.evaluation_context.dense_policy.blas_max_threads = 2;
|
||||
},
|
||||
[](Assembly& a) {
|
||||
a.trial_constraints->shells[0U]
|
||||
.evaluation_context.dense_policy.dynamic = 1;
|
||||
},
|
||||
[](Assembly& a) {
|
||||
a.trial_constraints->shells[0U]
|
||||
.evaluation_context.dense_policy.dynamic = -1;
|
||||
},
|
||||
[](Assembly& a) {
|
||||
a.trial_constraints->shells[0U].evaluation_context.mxcsr_control ^=
|
||||
0x8000U;
|
||||
},
|
||||
[](Assembly& a) {
|
||||
a.trial_constraints->shells[0U].evaluation_context.supported = false;
|
||||
}};
|
||||
for (std::size_t i = 0U; i < 64U; ++i)
|
||||
changes.push_back([i](Assembly& a) {
|
||||
a.trial_constraints->shells[0U].configuration.values[i] += 0.125;
|
||||
});
|
||||
for (const double invalid : {std::numeric_limits<double>::quiet_NaN(),
|
||||
std::numeric_limits<double>::infinity(),
|
||||
-std::numeric_limits<double>::infinity()})
|
||||
changes.push_back([invalid](Assembly& a) {
|
||||
a.trial_constraints->shells[0U].configuration.values[60U] = invalid;
|
||||
});
|
||||
for (std::size_t i = 0U; i < changes.size(); ++i) {
|
||||
SCOPED_TRACE(i);
|
||||
auto candidate = assembled.Value();
|
||||
candidate.trial_constraints->shells[0U].drilling_constraint[0U] = 17.0;
|
||||
changes[i](candidate);
|
||||
auto fresh = candidate;
|
||||
fresh.trial_constraints.reset();
|
||||
const auto reference = evaluate(fresh);
|
||||
const auto actual = evaluate(candidate);
|
||||
ASSERT_TRUE(reference.HasValue());
|
||||
ASSERT_TRUE(actual.HasValue());
|
||||
ExpectSameOperators(actual.Value(), reference.Value());
|
||||
}
|
||||
for (std::size_t kind = 0U; kind < 2U; ++kind) {
|
||||
auto candidate = assembled.Value();
|
||||
if (kind == 0U) candidate.trial_constraints->shells.clear();
|
||||
if (kind == 1U) candidate.trial_constraints.reset();
|
||||
auto fresh = assembled.Value();
|
||||
fresh.trial_constraints.reset();
|
||||
const auto reference = evaluate(fresh);
|
||||
const auto actual = evaluate(candidate);
|
||||
ASSERT_TRUE(reference.HasValue());
|
||||
ASSERT_TRUE(actual.HasValue());
|
||||
ExpectSameOperators(actual.Value(), reference.Value());
|
||||
}
|
||||
// Change the actual consumer environment, preserving the original fallback.
|
||||
for (std::size_t mode = 0U; mode < 5U; ++mode) {
|
||||
SCOPED_TRACE(mode);
|
||||
auto candidate = assembled.Value();
|
||||
candidate.trial_constraints->shells[0U].drilling_constraint[0U] = 17.0;
|
||||
auto fresh = candidate;
|
||||
fresh.trial_constraints.reset();
|
||||
#if defined(_M_X64)
|
||||
const auto csr = _mm_getcsr();
|
||||
if (mode == 0U) _mm_setcsr(csr ^ 0x8000U);
|
||||
if (mode == 1U) _mm_setcsr(csr ^ 0x0040U);
|
||||
#endif
|
||||
const int rounding = std::fegetround();
|
||||
if (mode == 2U) static_cast<void>(std::fesetround(FE_DOWNWARD));
|
||||
if (mode == 3U) static_cast<void>(mkl_set_num_threads_local(2));
|
||||
if (mode == 4U) mkl_set_dynamic(1);
|
||||
const auto reference = evaluate(fresh);
|
||||
const auto actual = evaluate(candidate);
|
||||
if (mode == 4U) mkl_set_dynamic(0);
|
||||
if (mode == 3U) EXPECT_EQ(mkl_set_num_threads_local(0), 2);
|
||||
static_cast<void>(std::fesetround(rounding));
|
||||
#if defined(_M_X64)
|
||||
_mm_setcsr(csr);
|
||||
#endif
|
||||
ASSERT_TRUE(reference.HasValue());
|
||||
ASSERT_TRUE(actual.HasValue());
|
||||
ExpectSameOperators(actual.Value(), reference.Value());
|
||||
}
|
||||
auto failed_trial = assembled.Value();
|
||||
failed_trial.frame.generalized_coordinates[0U] =
|
||||
std::numeric_limits<double>::infinity();
|
||||
auto fresh_failure = failed_trial;
|
||||
fresh_failure.trial_constraints.reset();
|
||||
const auto failed = evaluate(failed_trial);
|
||||
const auto original = evaluate(fresh_failure);
|
||||
ASSERT_FALSE(failed.HasValue());
|
||||
ASSERT_FALSE(original.HasValue());
|
||||
ASSERT_EQ(failed.GetStatus().Diagnostics().size(),
|
||||
original.GetStatus().Diagnostics().size());
|
||||
EXPECT_EQ(failed.GetStatus().Diagnostics()[0U].code,
|
||||
original.GetStatus().Diagnostics()[0U].code);
|
||||
EXPECT_EQ(failed.GetStatus().Diagnostics()[0U].message,
|
||||
original.GetStatus().Diagnostics()[0U].message);
|
||||
const auto rerun = evaluate(assembled.Value());
|
||||
auto fresh = assembled.Value();
|
||||
fresh.trial_constraints.reset();
|
||||
const auto reference = evaluate(fresh);
|
||||
ASSERT_TRUE(rerun.HasValue());
|
||||
ASSERT_TRUE(reference.HasValue());
|
||||
ExpectSameOperators(rerun.Value(), reference.Value());
|
||||
}
|
||||
|
||||
TEST(HhtReducedOperators, TrialContextControlsAndInitialFalseFailureLifetime) {
|
||||
RestoreTrialEnvironment restore;
|
||||
const auto context = fesa::hht_internal::ReadTrialEvaluationContext();
|
||||
ASSERT_TRUE(fesa::hht_internal::ReusableTrialContext(context, context));
|
||||
for (const unsigned int bit : {0x0040U, 0x8000U, 0x2000U, 0x0080U}) {
|
||||
auto changed = context;
|
||||
changed.mxcsr_control ^= bit;
|
||||
EXPECT_FALSE(fesa::hht_internal::ReusableTrialContext(context, changed));
|
||||
}
|
||||
auto unmasked = context;
|
||||
unmasked.mxcsr_control &= ~0x0080U;
|
||||
EXPECT_FALSE(fesa::hht_internal::ReusableTrialContext(unmasked, unmasked));
|
||||
static_cast<void>(mkl_set_num_threads_local(2));
|
||||
const auto positive = fesa::hht_internal::ReadTrialEvaluationContext();
|
||||
EXPECT_FALSE(fesa::hht_internal::ReusableTrialContext(positive, positive));
|
||||
EXPECT_EQ(mkl_set_num_threads_local(0), 2);
|
||||
mkl_set_dynamic(1);
|
||||
const auto dynamic = fesa::hht_internal::ReadTrialEvaluationContext();
|
||||
EXPECT_FALSE(fesa::hht_internal::ReusableTrialContext(dynamic, dynamic));
|
||||
mkl_set_dynamic(0);
|
||||
const auto fixture = MakeFixture(false);
|
||||
const auto shells =
|
||||
fesa::hht_internal::BuildRuntimeShells(*fixture.domain, fixture.dofs);
|
||||
ASSERT_TRUE(shells.HasValue());
|
||||
const fesa::Vector zero(fixture.dofs.FullDofCount());
|
||||
const auto position =
|
||||
Assemble(fixture, shells.Value(), zero, zero, zero, zero, false);
|
||||
ASSERT_TRUE(position.HasValue());
|
||||
EXPECT_FALSE(position.Value().trial_constraints.has_value());
|
||||
mkl_set_dynamic(1);
|
||||
const auto dynamic_trial =
|
||||
Assemble(fixture, shells.Value(), zero, zero, zero, zero, true);
|
||||
mkl_set_dynamic(0);
|
||||
ASSERT_TRUE(dynamic_trial.HasValue());
|
||||
ASSERT_TRUE(dynamic_trial.Value().trial_constraints.has_value());
|
||||
EXPECT_FALSE(
|
||||
dynamic_trial.Value().trial_constraints->shells[0U].directional_internal);
|
||||
static_cast<void>(mkl_set_num_threads_local(2));
|
||||
const auto positive_trial =
|
||||
Assemble(fixture, shells.Value(), zero, zero, zero, zero, true);
|
||||
EXPECT_EQ(mkl_set_num_threads_local(0), 2);
|
||||
ASSERT_TRUE(positive_trial.HasValue());
|
||||
ASSERT_TRUE(positive_trial.Value().trial_constraints.has_value());
|
||||
EXPECT_FALSE(positive_trial.Value()
|
||||
.trial_constraints->shells[0U]
|
||||
.directional_internal);
|
||||
fesa::DynamicAcceptedFrameState frame{};
|
||||
frame.is_initial = true;
|
||||
for (auto* vector :
|
||||
{&frame.generalized_coordinates, &frame.velocity, &frame.acceleration,
|
||||
&frame.algorithmic_acceleration, &frame.external_force})
|
||||
*vector = zero;
|
||||
fesa::SerialParallelFor parallel;
|
||||
const auto parameters = fesa::MakeHhtParameters(-0.05);
|
||||
ASSERT_TRUE(parameters.HasValue());
|
||||
const auto initial = fesa::hht_internal::EvaluateAssembly(
|
||||
*fixture.domain, fixture.dofs, shells.Value(), frame, zero, 0.1,
|
||||
parameters.Value(), parallel, true);
|
||||
ASSERT_TRUE(initial.HasValue());
|
||||
EXPECT_FALSE(initial.Value().trial_constraints.has_value());
|
||||
auto invalid = zero;
|
||||
invalid[0U] = std::numeric_limits<double>::quiet_NaN();
|
||||
const auto failure =
|
||||
Assemble(fixture, shells.Value(), invalid, zero, zero, zero, true);
|
||||
EXPECT_FALSE(failure.HasValue());
|
||||
const auto current =
|
||||
Assemble(fixture, shells.Value(), zero, zero, zero, zero, true);
|
||||
const auto next =
|
||||
Assemble(fixture, shells.Value(), zero, zero, zero, zero, true);
|
||||
ASSERT_TRUE(current.HasValue());
|
||||
ASSERT_TRUE(next.HasValue());
|
||||
ASSERT_EQ(current.Value().trial_constraints->shells.size(),
|
||||
shells.Value().size());
|
||||
ASSERT_EQ(next.Value().trial_constraints->shells.size(),
|
||||
shells.Value().size());
|
||||
EXPECT_NE(¤t.Value().trial_constraints->shells[0U],
|
||||
&next.Value().trial_constraints->shells[0U]);
|
||||
}
|
||||
|
||||
TEST(HhtReducedOperators, NonfiniteMatchingTrialKeysPreserveOriginalFailure) {
|
||||
RestoreTrialEnvironment restore;
|
||||
const auto fixture = MakeFixture(false);
|
||||
const auto shells =
|
||||
fesa::hht_internal::BuildRuntimeShells(*fixture.domain, fixture.dofs);
|
||||
ASSERT_TRUE(shells.HasValue());
|
||||
const fesa::Vector zero(fixture.dofs.FullDofCount());
|
||||
const auto assembled =
|
||||
Assemble(fixture, shells.Value(), zero, zero, zero, zero, true);
|
||||
ASSERT_TRUE(assembled.HasValue());
|
||||
ASSERT_TRUE(assembled.Value().trial_constraints.has_value());
|
||||
ASSERT_TRUE(
|
||||
assembled.Value().trial_constraints->shells[0U].directional_internal);
|
||||
const auto chart = fesa::hht_reduced_internal::BuildFixedChart(
|
||||
fixture.dofs, assembled.Value().rotations);
|
||||
ASSERT_TRUE(chart.HasValue());
|
||||
const auto evaluate = [&](const fesa::hht_internal::DynamicAssembly& value) {
|
||||
return fesa::hht_reduced_internal::EvaluateConstraintOperators(
|
||||
*fixture.domain, fixture.dofs, shells.Value(), value, chart.Value(),
|
||||
zero, zero);
|
||||
};
|
||||
const std::array<double, 3> invalid{std::numeric_limits<double>::quiet_NaN(),
|
||||
std::numeric_limits<double>::infinity(),
|
||||
-std::numeric_limits<double>::infinity()};
|
||||
for (std::size_t channel = 0U; channel < 2U; ++channel)
|
||||
for (std::size_t i = 0U; i < invalid.size(); ++i) {
|
||||
SCOPED_TRACE(channel);
|
||||
SCOPED_TRACE(i);
|
||||
auto candidate = assembled.Value();
|
||||
auto& saved = candidate.trial_constraints->shells[0U];
|
||||
if (channel == 0U) {
|
||||
candidate.frame.generalized_coordinates[0U] = invalid[i];
|
||||
saved.q[0U] = invalid[i];
|
||||
} else {
|
||||
candidate.frame.velocity[0U] = invalid[i];
|
||||
saved.v[0U] = invalid[i];
|
||||
}
|
||||
auto fresh = candidate;
|
||||
fresh.trial_constraints.reset();
|
||||
const auto original = evaluate(fresh);
|
||||
const auto actual = evaluate(candidate);
|
||||
ASSERT_FALSE(original.HasValue());
|
||||
ASSERT_FALSE(actual.HasValue());
|
||||
EXPECT_EQ(actual.GetStatus().Category(), original.GetStatus().Category());
|
||||
const auto& a = actual.GetStatus().Diagnostics();
|
||||
const auto& b = original.GetStatus().Diagnostics();
|
||||
ASSERT_EQ(a.size(), b.size());
|
||||
for (std::size_t j = 0U; j < a.size(); ++j) {
|
||||
EXPECT_EQ(a[j].severity, b[j].severity);
|
||||
EXPECT_EQ(a[j].code, b[j].code);
|
||||
EXPECT_EQ(a[j].location.file, b[j].location.file);
|
||||
EXPECT_EQ(a[j].location.line, b[j].location.line);
|
||||
EXPECT_EQ(a[j].keyword, b[j].keyword);
|
||||
EXPECT_EQ(a[j].entity_identity, b[j].entity_identity);
|
||||
EXPECT_EQ(a[j].message, b[j].message);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
TEST(HhtReducedOperators, NonfiniteMatchingTimeKeyMissPreservesFreshSuccess) {
|
||||
RestoreTrialEnvironment restore;
|
||||
const auto fixture = MakeFixture(false);
|
||||
const auto shells =
|
||||
fesa::hht_internal::BuildRuntimeShells(*fixture.domain, fixture.dofs);
|
||||
ASSERT_TRUE(shells.HasValue());
|
||||
const fesa::Vector zero(fixture.dofs.FullDofCount());
|
||||
const auto assembled =
|
||||
Assemble(fixture, shells.Value(), zero, zero, zero, zero, true);
|
||||
ASSERT_TRUE(assembled.HasValue());
|
||||
ASSERT_TRUE(assembled.Value().trial_constraints.has_value());
|
||||
const auto chart = fesa::hht_reduced_internal::BuildFixedChart(
|
||||
fixture.dofs, assembled.Value().rotations);
|
||||
ASSERT_TRUE(chart.HasValue());
|
||||
const auto evaluate = [&](const fesa::hht_internal::DynamicAssembly& value) {
|
||||
return fesa::hht_reduced_internal::EvaluateConstraintOperators(
|
||||
*fixture.domain, fixture.dofs, shells.Value(), value, chart.Value(),
|
||||
zero, zero);
|
||||
};
|
||||
const auto parameters = fesa::MakeHhtParameters(-0.05);
|
||||
ASSERT_TRUE(parameters.HasValue());
|
||||
fesa::SerialParallelFor parallel;
|
||||
for (const double bad_time : {std::numeric_limits<double>::quiet_NaN(),
|
||||
std::numeric_limits<double>::infinity(),
|
||||
-std::numeric_limits<double>::infinity()}) {
|
||||
auto candidate = assembled.Value();
|
||||
candidate.frame.time = bad_time;
|
||||
candidate.trial_constraints->time = bad_time;
|
||||
candidate.trial_constraints->shells[0U].drilling_constraint[0U] = 17.0;
|
||||
auto fresh = candidate;
|
||||
fresh.trial_constraints.reset();
|
||||
const auto reference = evaluate(fresh);
|
||||
const auto actual = evaluate(candidate);
|
||||
ASSERT_TRUE(reference.HasValue());
|
||||
ASSERT_TRUE(actual.HasValue());
|
||||
ExpectSameOperators(actual.Value(), reference.Value());
|
||||
const auto producer = fesa::hht_internal::EvaluateAssembly(
|
||||
*fixture.domain, fixture.dofs, shells.Value(), candidate.frame, zero,
|
||||
0.1, parameters.Value(), parallel, true);
|
||||
ASSERT_TRUE(producer.HasValue());
|
||||
EXPECT_FALSE(producer.Value().trial_constraints.has_value());
|
||||
const auto producer_result = evaluate(producer.Value());
|
||||
ASSERT_TRUE(producer_result.HasValue());
|
||||
ExpectSameOperators(producer_result.Value(), reference.Value());
|
||||
}
|
||||
}
|
||||
|
||||
TEST(HhtReducedOperators, ScatterShellDerivativesByConstraintRow) {
|
||||
const auto fixture = MakeFixture(false);
|
||||
const auto shells = fesa::hht_internal::BuildRuntimeShells(*fixture.domain,
|
||||
@@ -1141,4 +1682,58 @@ TEST(HhtReducedChannelNewton, RestrictedSingularityIsNotFullInvertibility) {
|
||||
EXPECT_FALSE(solver.FactorizeFresh(restricted.Value().tangent).IsOk());
|
||||
}
|
||||
|
||||
TEST(HhtReducedOperators, NullMetricKeepsFiniteLeftAssociatedProducts) {
|
||||
const auto fixture = MakeFixture(false);
|
||||
const auto shells = fesa::hht_internal::BuildRuntimeShells(*fixture.domain,
|
||||
fixture.dofs);
|
||||
ASSERT_TRUE(shells.HasValue());
|
||||
const fesa::Vector zero(fixture.dofs.FullDofCount());
|
||||
const auto assembled = Assemble(fixture, shells.Value(), zero, zero, zero,
|
||||
zero, false);
|
||||
ASSERT_TRUE(assembled.HasValue());
|
||||
auto assembly = assembled.Value();
|
||||
const double maximum = (std::numeric_limits<double>::max)();
|
||||
const double epsilon = std::ldexp(1.0, -26);
|
||||
const double t = std::sqrt(1.0 - epsilon * epsilon);
|
||||
const std::array<double, 3U> n{epsilon, 0.6 * t, 0.8 * t};
|
||||
const std::array<double, 9U> block{0.0, maximum, maximum,
|
||||
maximum, 0.0, 0.0,
|
||||
maximum, 0.0, 0.0};
|
||||
double original_metric = 0.0;
|
||||
for (std::size_t i = 0U; i < 3U; ++i)
|
||||
for (std::size_t j = 0U; j < 3U; ++j)
|
||||
original_metric += (n[i] * block[3U * i + j]) * n[j];
|
||||
ASSERT_TRUE(std::isfinite(original_metric));
|
||||
ASSERT_GT(original_metric, 0.0);
|
||||
ASSERT_FALSE(std::isfinite(block[1U] * n[1U] + block[2U] * n[2U]));
|
||||
std::vector<fesa::CooContribution> entries;
|
||||
for (std::size_t node = 0U; node < assembly.rotations.size(); ++node) {
|
||||
assembly.rotations[node].drill_null = fesa::Vector3(n);
|
||||
for (std::size_t i = 0U; i < 3U; ++i)
|
||||
for (std::size_t j = 0U; j < 3U; ++j)
|
||||
entries.push_back({6U * node + 3U + i, 6U * node + 3U + j,
|
||||
block[3U * i + j], node, 3U * i + j});
|
||||
}
|
||||
const auto metric = fesa::hht_internal::MakeSparse(
|
||||
fixture.dofs.FullDofCount(), fixture.dofs.FullDofCount(),
|
||||
std::move(entries));
|
||||
ASSERT_TRUE(metric.HasValue());
|
||||
assembly.drilling_metric = metric.Value();
|
||||
const auto chart = fesa::hht_reduced_internal::BuildFixedChart(
|
||||
fixture.dofs, assembly.rotations);
|
||||
ASSERT_TRUE(chart.HasValue());
|
||||
fesa::hht_reduced_internal::ConstraintOperators operators;
|
||||
operators.rows.resize(chart.Value().null_nodes.size());
|
||||
for (std::size_t row = 0U; row < operators.rows.size(); ++row)
|
||||
for (std::size_t component = 0U; component < 3U; ++component)
|
||||
operators.rows[row].gradient.push_back(
|
||||
{6U * chart.Value().null_nodes[row] + 3U + component,
|
||||
original_metric * n[component]});
|
||||
fesa::MklPardisoTangentSolver solver;
|
||||
const auto checked = fesa::hht_reduced_internal::CheckGraphRegularity(
|
||||
assembly, chart.Value(), operators, solver);
|
||||
ASSERT_TRUE(checked.HasValue());
|
||||
EXPECT_GE(checked.Value(), std::ldexp(1.0, -32));
|
||||
}
|
||||
|
||||
} // namespace
|
||||
|
||||
@@ -481,3 +481,47 @@ TEST(LoadAssembly, ZeroLoadsRemainZero) {
|
||||
ASSERT_TRUE(constrained_rhs.HasValue());
|
||||
EXPECT_EQ(constrained_rhs.Value().Size(), 0U);
|
||||
}
|
||||
|
||||
TEST(LoadAssembly, PreservesOrderedCancellationInPrescribedCorrection) {
|
||||
const std::filesystem::path source{"models/load-assembly.inp"};
|
||||
auto fixture = MakeFixture(
|
||||
1U, {},
|
||||
{{"10", 1, 1, 1.0, {source, 21U}},
|
||||
{"10", 3, 3, 1.0, {source, 22U}},
|
||||
{"10", 5, 5, 1.0, {source, 23U}}},
|
||||
{});
|
||||
const double large = 72057594037927936.0; // 2^56, exactly representable.
|
||||
const auto kfc = MakeDenseSparse(
|
||||
3U, 3U, {large, 1.0, -large, large, -large, 1.0, 0.0, 0.0, 0.0});
|
||||
|
||||
const auto rhs = fesa::LoadAssembler::EffectiveFreeRhs(
|
||||
fesa::Vector{6U}, kfc, fixture.dofs->PrescribedValues(), *fixture.dofs);
|
||||
|
||||
ASSERT_TRUE(rhs.HasValue());
|
||||
ASSERT_EQ(rhs.Value().Size(), 3U);
|
||||
EXPECT_DOUBLE_EQ(rhs.Value()[0U], 0.0);
|
||||
EXPECT_DOUBLE_EQ(rhs.Value()[1U], -1.0);
|
||||
EXPECT_DOUBLE_EQ(rhs.Value()[2U], 0.0);
|
||||
}
|
||||
|
||||
TEST(LoadAssembly, SelectsFirstOrderedOverflowDiagnostic) {
|
||||
const std::filesystem::path source{"models/load-assembly.inp"};
|
||||
auto fixture = MakeFixture(
|
||||
1U, {},
|
||||
{{"10", 1, 1, 1.0, {source, 21U}},
|
||||
{"10", 3, 3, 1.0, {source, 22U}},
|
||||
{"10", 5, 5, 2.0, {source, 23U}}},
|
||||
{});
|
||||
const double maximum = (std::numeric_limits<double>::max)();
|
||||
const auto kfc = MakeDenseSparse(
|
||||
3U, 3U, {maximum, maximum, 0.0, 0.0, 0.0, maximum, 0.0, 0.0, 0.0});
|
||||
|
||||
const auto rhs = fesa::LoadAssembler::EffectiveFreeRhs(
|
||||
fesa::Vector{6U}, kfc, fixture.dofs->PrescribedValues(), *fixture.dofs);
|
||||
|
||||
ExpectFailureCode(rhs, "nonfinite-load-accumulation");
|
||||
ASSERT_EQ(rhs.GetStatus().Diagnostics().size(), 1U);
|
||||
EXPECT_EQ(rhs.GetStatus().Diagnostics()[0U].entity_identity, "0");
|
||||
EXPECT_NE(rhs.GetStatus().Diagnostics()[0U].message.find("row sum"),
|
||||
std::string::npos);
|
||||
}
|
||||
|
||||
@@ -196,6 +196,21 @@ TEST(FiniteRotation,
|
||||
const Matrix left_jacobian = LeftJacobianSO3(phi);
|
||||
EXPECT_TRUE(IsFinite(left_jacobian));
|
||||
|
||||
// Preserve the original complete inverse-action check through the solve API.
|
||||
for (std::size_t column = 0; column < kRotationDimension; ++column) {
|
||||
const Vector3 basis{column == 0 ? 1.0 : 0.0,
|
||||
column == 1 ? 1.0 : 0.0,
|
||||
column == 2 ? 1.0 : 0.0};
|
||||
const auto solved = SpatialMomentSO3(phi, basis);
|
||||
ASSERT_TRUE(solved.HasValue());
|
||||
EXPECT_TRUE(std::isfinite(solved.Value().X()));
|
||||
EXPECT_TRUE(std::isfinite(solved.Value().Y()));
|
||||
EXPECT_TRUE(std::isfinite(solved.Value().Z()));
|
||||
const auto identity_column = Multiply(Transpose(left_jacobian), solved.Value());
|
||||
for (std::size_t row = 0; row < kRotationDimension; ++row)
|
||||
EXPECT_NEAR(identity_column[row], row == column ? 1.0 : 0.0, 1.0e-11);
|
||||
}
|
||||
|
||||
const Vector3 load{0.7, -0.2, 0.4};
|
||||
const auto spatial = SpatialMomentSO3(phi, load);
|
||||
ASSERT_TRUE(spatial.HasValue());
|
||||
|
||||
@@ -1180,6 +1180,35 @@ TEST(Hex8Element, MeanVolumeWarpedLowOnlyStateRetainsWeightedCubicEnergy) {
|
||||
EXPECT_NEAR(actual_cubic.high, cubic * c * c * c, 1e-11 * c * c * c);
|
||||
EXPECT_NE(actual_cubic.high, 0);
|
||||
}
|
||||
TEST(Hex8Element, BackendOperandRejectionRetainsOriginalStiffnessDiagnostic) {
|
||||
Coordinates coordinates{};
|
||||
for (std::size_t a = 0; a < 8; ++a)
|
||||
for (std::size_t i = 0; i < 3; ++i)
|
||||
coordinates[a][i] = 0.01 * kSigns[a][i];
|
||||
// Original native probe: finite moduli/volume, but mu*gradient overflows.
|
||||
// The failed diagnostic candidate must not become a scalar success fallback.
|
||||
const auto element = Make(coordinates, 1e308, -0.5);
|
||||
ASSERT_FALSE(element.HasValue());
|
||||
EXPECT_EQ(element.GetStatus().Diagnostics()[0].code, "invalid-hex8");
|
||||
EXPECT_EQ(element.GetStatus().Diagnostics()[0].message,
|
||||
"Hex8 reference stiffness is nonfinite.");
|
||||
}
|
||||
|
||||
TEST(Hex8Element, TensorFailureRetainsPriorityOverEnergyAndTangentOverflow) {
|
||||
Coordinates coordinates{};
|
||||
for (std::size_t a = 0; a < 8; ++a)
|
||||
for (std::size_t i = 0; i < 3; ++i)
|
||||
coordinates[a][i] = 0.01 * kSigns[a][i];
|
||||
const auto element = Make(coordinates, 1e200, -0.5);
|
||||
ASSERT_TRUE(element.HasValue());
|
||||
const auto displacement = Affine(coordinates,
|
||||
Tensor{{{1e100, 0, 0}, {0, 1e100, 0}, {0, 0, 1e100}}});
|
||||
const auto response = element.Value().EvaluateNonlinear(displacement);
|
||||
ASSERT_FALSE(response.HasValue());
|
||||
EXPECT_EQ(response.GetStatus().Diagnostics()[0].code, "invalid-hex8");
|
||||
EXPECT_EQ(response.GetStatus().Diagnostics()[0].message,
|
||||
"Hex8 trial tensor is nonfinite.");
|
||||
}
|
||||
} // namespace
|
||||
|
||||
TEST(Hex8Element, RejectsNonfiniteCanonicalJacobianActionBeforeFiniteGradients) {
|
||||
|
||||
@@ -2,16 +2,836 @@
|
||||
|
||||
#include <gtest/gtest.h>
|
||||
|
||||
#include <array>
|
||||
#include <atomic>
|
||||
#include <cfenv>
|
||||
#include <cmath>
|
||||
#include <cstdint>
|
||||
#include <cstring>
|
||||
#include <future>
|
||||
#include <limits>
|
||||
#include <random>
|
||||
#include <thread>
|
||||
#include <type_traits>
|
||||
#include <utility>
|
||||
#include <vector>
|
||||
|
||||
#include "fesa/materials/isotropic_linear_elastic_material.h"
|
||||
#include "../../../src/fesa/math/high_low_arithmetic.h"
|
||||
#include "../../../src/fesa/elements/hex8_geometry.h"
|
||||
#include "../../../src/fesa/elements/hex8_pair_simd.h"
|
||||
#include "../math/high_low_arithmetic_original.h"
|
||||
|
||||
namespace {
|
||||
using fesa::math_internal::HighLow;
|
||||
using fesa::math_internal::Subtract;
|
||||
|
||||
std::uint64_t PairBits(double value) {
|
||||
std::uint64_t bits = 0;
|
||||
std::memcpy(&bits, &value, sizeof(bits));
|
||||
return bits;
|
||||
}
|
||||
|
||||
void ExpectOriginalProduct(HighLow left, HighLow right) {
|
||||
const auto actual = fesa::math_internal::Multiply(left, right);
|
||||
const auto expected = fesa::high_low_original::Multiply(
|
||||
{left.high, left.low}, {right.high, right.low});
|
||||
EXPECT_EQ(PairBits(actual.high), PairBits(expected.high));
|
||||
EXPECT_EQ(PairBits(actual.low), PairBits(expected.low));
|
||||
const auto actual_sum = fesa::math_internal::Add(left, right);
|
||||
const auto expected_sum = fesa::high_low_original::Add(
|
||||
{left.high, left.low}, {right.high, right.low});
|
||||
EXPECT_EQ(PairBits(actual_sum.high), PairBits(expected_sum.high));
|
||||
EXPECT_EQ(PairBits(actual_sum.low), PairBits(expected_sum.low));
|
||||
}
|
||||
|
||||
TEST(Hex8HighLow, ScalarCrossProductShortcutMatchesOriginalBits) {
|
||||
ASSERT_TRUE(fesa::math_internal::ArithmeticEnvironmentSupported());
|
||||
const double minimum = std::numeric_limits<double>::denorm_min();
|
||||
const double maximum = std::numeric_limits<double>::max();
|
||||
const double infinity = std::numeric_limits<double>::infinity();
|
||||
const double nan = std::numeric_limits<double>::quiet_NaN();
|
||||
std::vector<HighLow> pairs{{}, {-0.0, 0.0}, {0.0, -0.0}, {-0.0, -0.0},
|
||||
{1, -0.0}, {-1, -0.0}, {1, 1}, {0, minimum}, {infinity, 0},
|
||||
{0, infinity}, {nan, 0}, {0, nan}, {maximum}, {-maximum},
|
||||
{minimum}, {-minimum}, {std::numeric_limits<double>::min()},
|
||||
{0.5}, {std::nextafter(0.5, 1.0)},
|
||||
{1, std::ldexp(1.0, -53)},
|
||||
{std::nextafter(1.0, 2.0), -std::ldexp(1.0, -53)}};
|
||||
for (const auto left : pairs)
|
||||
for (const auto right : pairs) ExpectOriginalProduct(left, right);
|
||||
for (int exponent = -1074; exponent <= 1023; ++exponent) {
|
||||
const double value = std::ldexp(1.0, exponent);
|
||||
for (double sign : {-1.0, 1.0})
|
||||
for (const auto right : pairs) {
|
||||
ExpectOriginalProduct(HighLow{sign * value}, right);
|
||||
ExpectOriginalProduct(right, HighLow{sign * value});
|
||||
}
|
||||
}
|
||||
std::mt19937_64 random(0x48e81234U);
|
||||
for (int sample = 0; sample < 12000; ++sample) {
|
||||
double left = 0;
|
||||
double right = 0;
|
||||
const auto left_bits = random();
|
||||
const auto right_bits = random();
|
||||
std::memcpy(&left, &left_bits, sizeof(left));
|
||||
std::memcpy(&right, &right_bits, sizeof(right));
|
||||
const auto pair = fesa::math_internal::TwoSum(left, right);
|
||||
ExpectOriginalProduct(pair, HighLow{});
|
||||
ExpectOriginalProduct(HighLow{}, pair);
|
||||
ExpectOriginalProduct(pair, HighLow{right});
|
||||
ExpectOriginalProduct(HighLow{right}, pair);
|
||||
ExpectOriginalProduct(pair, pair);
|
||||
}
|
||||
}
|
||||
|
||||
fesa::hex8_internal::PacketPair RawPacketPair(HighLow value) {
|
||||
return {value.high, value.low};
|
||||
}
|
||||
|
||||
fesa::hex8_internal::PairPacket FrozenMaterialPacket(
|
||||
const fesa::hex8_internal::MaterialPacketInput& input) {
|
||||
using Original = fesa::high_low_original::HighLow;
|
||||
const auto original = [](fesa::hex8_internal::PacketPair value) {
|
||||
return Original{value.high, value.low};
|
||||
};
|
||||
fesa::hex8_internal::PairPacket result;
|
||||
for (std::size_t lane = 0; lane < 4; ++lane) {
|
||||
const auto first = fesa::high_low_original::Multiply(
|
||||
original(input.deviatoric_left.values[lane]),
|
||||
original(input.deviatoric_right.values[lane]));
|
||||
const auto second = fesa::high_low_original::Multiply(
|
||||
original(input.shear_left.values[lane]), original(input.shear_right.values[lane]));
|
||||
const auto third = fesa::high_low_original::Multiply(
|
||||
original(input.tensor_left.values[lane]), original(input.gradient_dot.values[lane]));
|
||||
const auto value = fesa::high_low_original::Add(
|
||||
fesa::high_low_original::Add(first, second), third);
|
||||
const auto accumulated = fesa::high_low_original::Add(
|
||||
original(input.accumulated.values[lane]),
|
||||
fesa::high_low_original::Multiply(value, original(input.weight)));
|
||||
result.values[lane] = {accumulated.high, accumulated.low};
|
||||
}
|
||||
return result;
|
||||
}
|
||||
|
||||
bool ExpectFrozenMaterialPacket(
|
||||
const fesa::hex8_internal::MaterialPacketInput& input) {
|
||||
const auto expected = FrozenMaterialPacket(input);
|
||||
fesa::hex8_internal::PairPacket scalar, selected;
|
||||
fesa::hex8_internal::EvaluateMaterialPacketScalar(input, &scalar);
|
||||
const auto evaluator = fesa::hex8_internal::SelectMaterialPacketEvaluator();
|
||||
evaluator(input, &selected);
|
||||
for (std::size_t lane = 0; lane < 4; ++lane) {
|
||||
SCOPED_TRACE(lane);
|
||||
EXPECT_EQ(PairBits(scalar.values[lane].high), PairBits(expected.values[lane].high));
|
||||
EXPECT_EQ(PairBits(scalar.values[lane].low), PairBits(expected.values[lane].low));
|
||||
EXPECT_EQ(PairBits(selected.values[lane].high), PairBits(expected.values[lane].high));
|
||||
EXPECT_EQ(PairBits(selected.values[lane].low), PairBits(expected.values[lane].low));
|
||||
}
|
||||
return evaluator != fesa::hex8_internal::EvaluateMaterialPacketScalar;
|
||||
}
|
||||
|
||||
TEST(Hex8HighLow, FourColumnMaterialPacketMatchesFrozenScalarBits) {
|
||||
ASSERT_TRUE(fesa::math_internal::ArithmeticEnvironmentSupported());
|
||||
using fesa::hex8_internal::MaterialPacketInput;
|
||||
RecordProperty("private_packet_backend",
|
||||
fesa::hex8_internal::SelectMaterialPacketEvaluator() ==
|
||||
fesa::hex8_internal::EvaluateMaterialPacketScalar ? "scalar" : "avx2");
|
||||
std::size_t packet_checks = 0, avx2_evaluator_checks = 0;
|
||||
const double tiny = std::numeric_limits<double>::denorm_min();
|
||||
const double maximum = std::numeric_limits<double>::max();
|
||||
const std::vector<HighLow> boundary{{}, {-0.0, 0}, {0, -0.0},
|
||||
{1}, {-1}, {1, -0.0}, {1, std::ldexp(1.0, -54)},
|
||||
{-1, std::ldexp(1.0, -54)}, {tiny}, {-tiny},
|
||||
{std::numeric_limits<double>::min()}, {maximum}, {-maximum},
|
||||
{1, tiny}, {1, -tiny}, {std::nextafter(1.0, 2.0)},
|
||||
{1, 1}, {0, tiny}, {std::numeric_limits<double>::infinity(), 0},
|
||||
{std::numeric_limits<double>::quiet_NaN(), 0},
|
||||
{std::numeric_limits<double>::signaling_NaN(), 0},
|
||||
{0, std::numeric_limits<double>::signaling_NaN()}};
|
||||
for (std::size_t first = 0; first < boundary.size(); ++first)
|
||||
for (std::size_t second = 0; second < boundary.size(); ++second) {
|
||||
MaterialPacketInput input{};
|
||||
input.weight = {0.125};
|
||||
for (std::size_t lane = 0; lane < 4; ++lane) {
|
||||
input.deviatoric_left.values[lane] = RawPacketPair(boundary[first]);
|
||||
input.deviatoric_right.values[lane] = RawPacketPair(boundary[second]);
|
||||
input.shear_left.values[lane] = {2, std::ldexp(1.0, -54)};
|
||||
input.shear_right.values[lane] = {-0.5, std::ldexp(1.0, -56)};
|
||||
input.tensor_left.values[lane] = {0.75};
|
||||
input.gradient_dot.values[lane] = {-0.25};
|
||||
input.accumulated.values[lane] = lane == 0 ? fesa::hex8_internal::PacketPair{0, 0}
|
||||
: fesa::hex8_internal::PacketPair{0.125, 0};
|
||||
}
|
||||
avx2_evaluator_checks += ExpectFrozenMaterialPacket(input) ? 1U : 0U;
|
||||
++packet_checks;
|
||||
}
|
||||
for (int exponent = -1074; exponent <= 1023; ++exponent) {
|
||||
MaterialPacketInput input{};
|
||||
input.weight = {1};
|
||||
for (std::size_t lane = 0; lane < 4; ++lane) {
|
||||
input.deviatoric_left.values[lane] = {
|
||||
std::ldexp(lane % 2U == 0 ? 1.0 : -1.0, exponent)};
|
||||
input.deviatoric_right.values[lane] = {lane < 2 ? 0.5 : 2.0};
|
||||
}
|
||||
avx2_evaluator_checks += ExpectFrozenMaterialPacket(input) ? 1U : 0U;
|
||||
++packet_checks;
|
||||
}
|
||||
std::mt19937_64 random(0x4c0116U);
|
||||
for (std::size_t sample = 0; sample < 2048; ++sample) {
|
||||
MaterialPacketInput input{};
|
||||
const auto pair = [&]() {
|
||||
const double high = std::ldexp(
|
||||
1.0 + static_cast<double>(random() % 256U) / 256.0,
|
||||
static_cast<int>(random() % 201U) - 100);
|
||||
const double signed_high = (random() & 1U) != 0 ? high : -high;
|
||||
const double low = sample % 3U == 0 ? 0.0 : std::ldexp(high, -55);
|
||||
return fesa::hex8_internal::PacketPair{
|
||||
signed_high, (random() & 1U) != 0 ? low : -low};
|
||||
};
|
||||
input.weight = sample % 2U == 0
|
||||
? fesa::hex8_internal::PacketPair{0.125, 0} : pair();
|
||||
for (std::size_t lane = 0; lane < 4; ++lane) {
|
||||
input.deviatoric_left.values[lane] = pair();
|
||||
input.deviatoric_right.values[lane] = pair();
|
||||
input.shear_left.values[lane] = pair();
|
||||
input.shear_right.values[lane] = pair();
|
||||
input.tensor_left.values[lane] = pair();
|
||||
input.gradient_dot.values[lane] = pair();
|
||||
input.accumulated.values[lane] = sample % 4U == 0
|
||||
? fesa::hex8_internal::PacketPair{0, 0} : pair();
|
||||
}
|
||||
avx2_evaluator_checks += ExpectFrozenMaterialPacket(input) ? 1U : 0U;
|
||||
++packet_checks;
|
||||
}
|
||||
RecordProperty("packet_oracle_checks", static_cast<int>(packet_checks));
|
||||
RecordProperty("avx2_evaluator_packet_checks",
|
||||
static_cast<int>(avx2_evaluator_checks));
|
||||
}
|
||||
|
||||
TEST(Hex8HighLow, PacketSpecialLaneDoesNotChangeOtherColumns) {
|
||||
fesa::hex8_internal::MaterialPacketInput input{};
|
||||
input.weight = {0.125};
|
||||
for (std::size_t lane = 0; lane < 4; ++lane) {
|
||||
input.deviatoric_left.values[lane] = {1, std::ldexp(1.0, -54)};
|
||||
input.deviatoric_right.values[lane] = {2, std::ldexp(1.0, -55)};
|
||||
input.shear_left.values[lane] = {0.5};
|
||||
input.shear_right.values[lane] = {-0.25};
|
||||
input.tensor_left.values[lane] = {0.75};
|
||||
input.gradient_dot.values[lane] = {0.125};
|
||||
}
|
||||
const auto reference = FrozenMaterialPacket(input);
|
||||
const std::vector<HighLow> special{{}, {-0.0, 0}, {1},
|
||||
{std::numeric_limits<double>::max()},
|
||||
{std::numeric_limits<double>::denorm_min()}, {1, 1},
|
||||
{std::numeric_limits<double>::quiet_NaN(), 0}};
|
||||
for (std::size_t lane = 0; lane < 4; ++lane)
|
||||
for (const auto value : special) {
|
||||
auto changed = input;
|
||||
changed.deviatoric_left.values[lane] = RawPacketPair(value);
|
||||
ExpectFrozenMaterialPacket(changed);
|
||||
fesa::hex8_internal::PairPacket actual;
|
||||
fesa::hex8_internal::SelectMaterialPacketEvaluator()(changed, &actual);
|
||||
for (std::size_t other = 0; other < 4; ++other)
|
||||
if (other != lane) {
|
||||
EXPECT_EQ(PairBits(actual.values[other].high), PairBits(reference.values[other].high));
|
||||
EXPECT_EQ(PairBits(actual.values[other].low), PairBits(reference.values[other].low));
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
TEST(Hex8HighLow, UniformDyadicPacketsExerciseEachLowZeroShape) {
|
||||
std::size_t checks = 0, avx2_checks = 0;
|
||||
for (int shape = 0; shape < 4; ++shape)
|
||||
for (int low_weight = 0; low_weight < 2; ++low_weight)
|
||||
for (int zero_accumulator = 0; zero_accumulator < 2; ++zero_accumulator) {
|
||||
fesa::hex8_internal::MaterialPacketInput input{};
|
||||
input.weight = {0.5, low_weight != 0 ? std::ldexp(1.0, -57) : 0.0};
|
||||
for (std::size_t lane = 0; lane < 4; ++lane) {
|
||||
const bool left_low = (shape & 1) != 0;
|
||||
const bool right_low = (shape & 2) != 0;
|
||||
// Every lane has the same normalized nonzero dyadic inputs. Component
|
||||
// LBE sums stay above -200 and all Add intermediates are bounded by 4.
|
||||
// Thus each Multiply low-shape is uniform and its component products
|
||||
// bypass zero/unsupported-tail fallback. No mixed-zero Add fallback
|
||||
// is possible; the initial zero accumulator is uniform across lanes.
|
||||
input.deviatoric_left.values[lane] = {1, left_low ? std::ldexp(1.0, -54) : 0};
|
||||
input.deviatoric_right.values[lane] = {2, right_low ? std::ldexp(1.0, -54) : 0};
|
||||
input.shear_left.values[lane] = {0.5, left_low ? std::ldexp(1.0, -56) : 0};
|
||||
input.shear_right.values[lane] = {0.25, right_low ? std::ldexp(1.0, -57) : 0};
|
||||
input.tensor_left.values[lane] = {0.75, left_low ? std::ldexp(1.0, -56) : 0};
|
||||
input.gradient_dot.values[lane] = {0.125, right_low ? std::ldexp(1.0, -58) : 0};
|
||||
input.accumulated.values[lane] = zero_accumulator != 0
|
||||
? fesa::hex8_internal::PacketPair{0, 0}
|
||||
: fesa::hex8_internal::PacketPair{0.0625, 0};
|
||||
}
|
||||
avx2_checks += ExpectFrozenMaterialPacket(input) ? 1U : 0U;
|
||||
++checks;
|
||||
}
|
||||
RecordProperty("uniform_low_shape_checks", static_cast<int>(checks));
|
||||
RecordProperty("avx2_uniform_low_shape_checks", static_cast<int>(avx2_checks));
|
||||
}
|
||||
|
||||
TEST(Hex8HighLow, OverflowLaneIsNeutralizedBeforeResidualFma) {
|
||||
const auto evaluator = fesa::hex8_internal::SelectMaterialPacketEvaluator();
|
||||
if (evaluator == fesa::hex8_internal::EvaluateMaterialPacketScalar)
|
||||
GTEST_SKIP() << "AVX2 masked environment is not selected; routing unverified.";
|
||||
std::fenv_t original;
|
||||
ASSERT_EQ(std::fegetenv(&original), 0);
|
||||
for (std::size_t bad = 0; bad < 4; ++bad) {
|
||||
fesa::hex8_internal::MaterialPacketInput input{};
|
||||
input.weight = {0.5};
|
||||
for (std::size_t lane = 0; lane < 4; ++lane) {
|
||||
input.deviatoric_left.values[lane] = {
|
||||
lane == bad ? std::numeric_limits<double>::max() : 1};
|
||||
input.deviatoric_right.values[lane] = {2};
|
||||
input.shear_left.values[lane] = {0.5};
|
||||
input.shear_right.values[lane] = {0.25};
|
||||
input.tensor_left.values[lane] = {0.75};
|
||||
input.gradient_dot.values[lane] = {0.125};
|
||||
input.accumulated.values[lane] = {0.0625};
|
||||
}
|
||||
// All operands are finite/nonzero and max*2 has LBE sum 972, so Product
|
||||
// reaches its vector multiply; only the post-product finite mask rejects it.
|
||||
const auto expected = FrozenMaterialPacket(input);
|
||||
EXPECT_EQ(std::feclearexcept(FE_ALL_EXCEPT), 0);
|
||||
fesa::hex8_internal::PairPacket output;
|
||||
evaluator(input, &output);
|
||||
const bool extra_invalid = (std::fetestexcept(FE_INVALID) & FE_INVALID) != 0;
|
||||
EXPECT_EQ(std::fesetenv(&original), 0);
|
||||
EXPECT_FALSE(extra_invalid);
|
||||
for (std::size_t lane = 0; lane < 4; ++lane) {
|
||||
EXPECT_EQ(PairBits(output.values[lane].high), PairBits(expected.values[lane].high));
|
||||
EXPECT_EQ(PairBits(output.values[lane].low), PairBits(expected.values[lane].low));
|
||||
}
|
||||
}
|
||||
RecordProperty("avx2_product_overflow_positions", 4);
|
||||
}
|
||||
|
||||
#if defined(_M_X64) || defined(__SSE2__)
|
||||
// Runs scalar and selected packet from identical FP state. The frozen original
|
||||
// supplies raw-bit results; the unchanged baseline supplies FE/MXCSR status.
|
||||
void ExpectPacketFlagsAndBits(
|
||||
const fesa::hex8_internal::MaterialPacketInput& input, bool prior_status) {
|
||||
std::fenv_t original;
|
||||
ASSERT_EQ(std::fegetenv(&original), 0);
|
||||
const auto original_csr = _mm_getcsr();
|
||||
const auto evaluator = fesa::hex8_internal::SelectMaterialPacketEvaluator();
|
||||
struct Observation {
|
||||
fesa::hex8_internal::PairPacket output;
|
||||
int flags;
|
||||
unsigned int status;
|
||||
};
|
||||
const auto observe = [&](fesa::hex8_internal::MaterialPacketEvaluator backend) {
|
||||
EXPECT_EQ(std::fesetenv(&original), 0);
|
||||
_mm_setcsr(original_csr & ~0x3fU);
|
||||
EXPECT_EQ(std::feclearexcept(FE_ALL_EXCEPT), 0);
|
||||
if (prior_status) {
|
||||
EXPECT_EQ(std::feraiseexcept(FE_INEXACT), 0);
|
||||
_mm_setcsr(_mm_getcsr() | 0x02U); // Preserve prior denormal status too.
|
||||
}
|
||||
Observation value{};
|
||||
backend(input, &value.output);
|
||||
value.flags = std::fetestexcept(FE_ALL_EXCEPT);
|
||||
value.status = _mm_getcsr() & 0x3fU;
|
||||
return value;
|
||||
};
|
||||
const auto scalar = observe(fesa::hex8_internal::EvaluateMaterialPacketScalar);
|
||||
const auto selected = observe(evaluator);
|
||||
const auto expected = FrozenMaterialPacket(input);
|
||||
// Restore both x87 and MXCSR before assertions, including NaN bit assertions.
|
||||
EXPECT_EQ(std::fesetenv(&original), 0);
|
||||
_mm_setcsr(original_csr);
|
||||
EXPECT_EQ(selected.flags, scalar.flags);
|
||||
EXPECT_EQ(selected.status, scalar.status);
|
||||
for (std::size_t lane = 0; lane < 4; ++lane) {
|
||||
SCOPED_TRACE(lane);
|
||||
EXPECT_EQ(PairBits(selected.output.values[lane].high),
|
||||
PairBits(expected.values[lane].high));
|
||||
EXPECT_EQ(PairBits(selected.output.values[lane].low),
|
||||
PairBits(expected.values[lane].low));
|
||||
EXPECT_EQ(PairBits(scalar.output.values[lane].high),
|
||||
PairBits(expected.values[lane].high));
|
||||
EXPECT_EQ(PairBits(scalar.output.values[lane].low),
|
||||
PairBits(expected.values[lane].low));
|
||||
}
|
||||
}
|
||||
|
||||
fesa::hex8_internal::MaterialPacketInput DyadicPacketFixture() {
|
||||
fesa::hex8_internal::MaterialPacketInput input{};
|
||||
input.weight = {0.5, 0};
|
||||
for (std::size_t lane = 0; lane < 4; ++lane) {
|
||||
input.deviatoric_left.values[lane] = {1, 0};
|
||||
input.deviatoric_right.values[lane] = {2, 0};
|
||||
input.shear_left.values[lane] = {0.5, 0};
|
||||
input.shear_right.values[lane] = {0.25, 0};
|
||||
input.tensor_left.values[lane] = {0.75, 0};
|
||||
input.gradient_dot.values[lane] = {0.125, 0};
|
||||
}
|
||||
return input;
|
||||
}
|
||||
|
||||
TEST(Hex8HighLow, PacketVectorGuardsPreserveScalarFlagsAndBits) {
|
||||
if (fesa::hex8_internal::SelectMaterialPacketEvaluator() ==
|
||||
fesa::hex8_internal::EvaluateMaterialPacketScalar)
|
||||
GTEST_SKIP() << "AVX2 masked environment is not selected.";
|
||||
using fesa::hex8_internal::PacketPair;
|
||||
const double maximum = std::numeric_limits<double>::max();
|
||||
const double snan = std::numeric_limits<double>::signaling_NaN();
|
||||
const double tiny = std::numeric_limits<double>::denorm_min();
|
||||
const std::vector<PacketPair> invalid_left{
|
||||
{-0.0, 0}, {0, -0.0}, {1, 1}, {snan, 0}, {0, snan}};
|
||||
const std::vector<PacketPair> dangerous_right{
|
||||
{maximum, maximum}, {snan, 0}, {0, snan}};
|
||||
std::size_t checks = 0;
|
||||
for (const auto left : invalid_left)
|
||||
for (const auto right : dangerous_right)
|
||||
for (std::size_t bad = 0; bad < 4; ++bad) {
|
||||
auto input = DyadicPacketFixture();
|
||||
input.deviatoric_left.values[bad] = left;
|
||||
input.deviatoric_right.values[bad] = right;
|
||||
// Later lanes must still contribute the unchanged bridge's RN status.
|
||||
const auto later = (bad + 1) % 4;
|
||||
input.deviatoric_left.values[later] = {1, std::ldexp(1.0, -54)};
|
||||
input.deviatoric_right.values[later] = {tiny, 0};
|
||||
ExpectPacketFlagsAndBits(input, false);
|
||||
ExpectPacketFlagsAndBits(input, true);
|
||||
checks += 2;
|
||||
}
|
||||
for (std::size_t lane = 0; lane < 4; ++lane) {
|
||||
auto mixed = DyadicPacketFixture();
|
||||
mixed.deviatoric_left.values[lane] = {1, std::ldexp(1.0, -54)};
|
||||
mixed.deviatoric_left.values[(lane + 1) % 4] = {maximum, maximum};
|
||||
ExpectPacketFlagsAndBits(mixed, false);
|
||||
ExpectPacketFlagsAndBits(mixed, true);
|
||||
auto signed_low = DyadicPacketFixture();
|
||||
signed_low.deviatoric_left.values[lane].low = -0.0;
|
||||
signed_low.accumulated.values[lane] = {-0.0, 0};
|
||||
ExpectPacketFlagsAndBits(signed_low, false);
|
||||
checks += 3;
|
||||
}
|
||||
RecordProperty("avx2_guard_flags_and_bit_checks", static_cast<int>(checks));
|
||||
}
|
||||
|
||||
TEST(Hex8HighLow, PacketTailScreenRetainsExactBoundaryAndFallback) {
|
||||
if (fesa::hex8_internal::SelectMaterialPacketEvaluator() ==
|
||||
fesa::hex8_internal::EvaluateMaterialPacketScalar)
|
||||
GTEST_SKIP() << "AVX2 masked environment is not selected.";
|
||||
const auto odd = [](int exponent) {
|
||||
return std::nextafter(std::ldexp(1.0, exponent),
|
||||
std::numeric_limits<double>::infinity());
|
||||
};
|
||||
const double tiny = std::numeric_limits<double>::denorm_min();
|
||||
const std::array<std::array<double, 2>, 8> operands{{
|
||||
{odd(-500), odd(-470)}, // screen true, exact LBE sum -1074
|
||||
{odd(-500), odd(-471)}, // screen false, exact rejection -1075
|
||||
{std::ldexp(1.0, -500), std::ldexp(1.0, -471)}, // false but supported
|
||||
{tiny, odd(52)}, {tiny, odd(51)}, {3 * tiny, odd(52)},
|
||||
{std::numeric_limits<double>::max(), 2}, {0, odd(52)}}};
|
||||
std::size_t checks = 0;
|
||||
for (const auto& pair : operands)
|
||||
for (std::size_t special = 0; special < 4; ++special) {
|
||||
fesa::hex8_internal::MaterialPacketInput input{};
|
||||
input.weight = {1, 0};
|
||||
for (std::size_t lane = 0; lane < 4; ++lane) {
|
||||
const double sign = lane % 2 == 0 ? 1.0 : -1.0;
|
||||
input.deviatoric_left.values[lane] =
|
||||
{sign * (lane == special ? pair[0] : odd(-500)), 0};
|
||||
input.deviatoric_right.values[lane] =
|
||||
{lane == special ? pair[1] : odd(-470), 0};
|
||||
}
|
||||
ExpectPacketFlagsAndBits(input, false);
|
||||
ExpectPacketFlagsAndBits(input, true);
|
||||
checks += 2;
|
||||
}
|
||||
RecordProperty("avx2_tail_screen_flags_and_bit_checks", static_cast<int>(checks));
|
||||
}
|
||||
#endif
|
||||
|
||||
#if defined(_M_X64) || defined(__SSE2__)
|
||||
fesa::hex8_internal::GeometryPacketOutput FrozenGeometryPacket(
|
||||
const fesa::hex8_internal::GeometryPacketInput& input) {
|
||||
const auto pair = [](fesa::hex8_internal::PacketPair value) {
|
||||
return fesa::high_low_original::HighLow{value.high, value.low};
|
||||
};
|
||||
fesa::hex8_internal::GeometryPacketOutput output{};
|
||||
for (std::size_t lane = 0; lane < 4; ++lane) {
|
||||
fesa::high_low_original::HighLow dot;
|
||||
for (std::size_t i = 0; i < 3; ++i)
|
||||
dot = fesa::high_low_original::Add(dot,
|
||||
fesa::high_low_original::Multiply(pair(input.gradient_a[i]),
|
||||
pair(input.gradient_b[i].values[lane])));
|
||||
fesa::high_low_original::HighLow geo;
|
||||
for (std::size_t j = 0; j < 3; ++j)
|
||||
for (std::size_t l = 0; l < 3; ++l)
|
||||
geo = fesa::high_low_original::Add(geo,
|
||||
fesa::high_low_original::Multiply(pair(input.gradient_stress[j][l]),
|
||||
pair(input.gradient_b[l].values[lane])));
|
||||
const auto weighted = fesa::high_low_original::Multiply(geo, pair(input.weight));
|
||||
output.gradient_dot.values[lane] = {dot.high, dot.low};
|
||||
output.weighted_geometric.values[lane] = {weighted.high, weighted.low};
|
||||
}
|
||||
return output;
|
||||
}
|
||||
|
||||
fesa::hex8_internal::GeometryPacketInput GeometryDyadicFixture() {
|
||||
fesa::hex8_internal::GeometryPacketInput input{};
|
||||
input.weight = {0.125, 0};
|
||||
for (std::size_t j = 0; j < 3; ++j) {
|
||||
input.gradient_a[j] = {static_cast<double>(j + 1) * 0.25, 0};
|
||||
for (std::size_t l = 0; l < 3; ++l) {
|
||||
// Deliberately asymmetric first-products and distinct b/component mapping.
|
||||
input.gradient_stress[j][l] =
|
||||
{static_cast<double>(1 + 3 * j + l) * 0.125, 0};
|
||||
for (std::size_t lane = 0; lane < 4; ++lane)
|
||||
input.gradient_b[l].values[lane] =
|
||||
{static_cast<double>(1 + 4 * l + lane) * 0.0625, 0};
|
||||
}
|
||||
}
|
||||
return input;
|
||||
}
|
||||
|
||||
// Original observation repeats geo*weight for three independent accumulators.
|
||||
// Selected observation reuses the weighted pair but retains each checked Add.
|
||||
void ExpectGeometryPacketBitsAndFlags(
|
||||
const fesa::hex8_internal::GeometryPacketInput& input, bool prior_status) {
|
||||
SCOPED_TRACE(prior_status);
|
||||
std::fenv_t original;
|
||||
ASSERT_EQ(std::fegetenv(&original), 0);
|
||||
const auto original_csr = _mm_getcsr();
|
||||
struct Observation {
|
||||
fesa::hex8_internal::GeometryPacketOutput output;
|
||||
fesa::hex8_internal::PairPacket accumulators[3];
|
||||
int flags;
|
||||
unsigned int status;
|
||||
};
|
||||
const auto current_pair = [](fesa::hex8_internal::PacketPair value) {
|
||||
return HighLow{value.high, value.low};
|
||||
};
|
||||
const auto observe = [&](bool original_order) {
|
||||
EXPECT_EQ(std::fesetenv(&original), 0);
|
||||
_mm_setcsr(original_csr & ~0x3fU);
|
||||
EXPECT_EQ(std::feclearexcept(FE_ALL_EXCEPT), 0);
|
||||
if (prior_status) {
|
||||
EXPECT_EQ(std::feraiseexcept(FE_INEXACT), 0);
|
||||
_mm_setcsr(_mm_getcsr() | 0x02U);
|
||||
}
|
||||
Observation value{};
|
||||
if (!original_order)
|
||||
fesa::hex8_internal::EvaluateGeometryPacketAvx2(input, &value.output);
|
||||
for (std::size_t lane = 0; lane < 4; ++lane) {
|
||||
HighLow geo;
|
||||
if (original_order) {
|
||||
HighLow dot;
|
||||
for (std::size_t i = 0; i < 3; ++i)
|
||||
dot = fesa::math_internal::Add(dot,
|
||||
fesa::math_internal::Multiply(current_pair(input.gradient_a[i]),
|
||||
current_pair(input.gradient_b[i].values[lane])));
|
||||
for (std::size_t j = 0; j < 3; ++j)
|
||||
for (std::size_t l = 0; l < 3; ++l)
|
||||
geo = fesa::math_internal::Add(geo,
|
||||
fesa::math_internal::Multiply(
|
||||
current_pair(input.gradient_stress[j][l]),
|
||||
current_pair(input.gradient_b[l].values[lane])));
|
||||
value.output.gradient_dot.values[lane] = {dot.high, dot.low};
|
||||
}
|
||||
const HighLow accumulators[3]{{},
|
||||
{static_cast<double>(lane + 1), std::ldexp(1.0, -54)}, {-1, -0.0}};
|
||||
for (std::size_t component = 0; component < 3; ++component) {
|
||||
const auto weighted = original_order
|
||||
? fesa::math_internal::Multiply(geo, current_pair(input.weight))
|
||||
: current_pair(value.output.weighted_geometric.values[lane]);
|
||||
if (original_order)
|
||||
value.output.weighted_geometric.values[lane] =
|
||||
{weighted.high, weighted.low};
|
||||
const auto accumulated = fesa::math_internal::Add(
|
||||
accumulators[component], weighted);
|
||||
value.accumulators[component].values[lane] =
|
||||
{accumulated.high, accumulated.low};
|
||||
}
|
||||
}
|
||||
value.flags = std::fetestexcept(FE_ALL_EXCEPT);
|
||||
value.status = _mm_getcsr() & 0x3fU;
|
||||
return value;
|
||||
};
|
||||
const auto baseline = observe(true);
|
||||
const auto selected = observe(false);
|
||||
fesa::hex8_internal::GeometryPacketOutput scalar;
|
||||
fesa::hex8_internal::EvaluateGeometryPacketScalar(input, &scalar);
|
||||
const auto expected = FrozenGeometryPacket(input);
|
||||
EXPECT_EQ(std::fesetenv(&original), 0);
|
||||
_mm_setcsr(original_csr);
|
||||
EXPECT_EQ(selected.flags, baseline.flags);
|
||||
EXPECT_EQ(selected.status, baseline.status);
|
||||
const auto same_bits = [](const fesa::hex8_internal::PairPacket& a,
|
||||
const fesa::hex8_internal::PairPacket& b) {
|
||||
for (std::size_t lane = 0; lane < 4; ++lane) {
|
||||
EXPECT_EQ(PairBits(a.values[lane].high), PairBits(b.values[lane].high));
|
||||
EXPECT_EQ(PairBits(a.values[lane].low), PairBits(b.values[lane].low));
|
||||
}
|
||||
};
|
||||
same_bits(selected.output.gradient_dot, expected.gradient_dot);
|
||||
same_bits(selected.output.weighted_geometric, expected.weighted_geometric);
|
||||
same_bits(scalar.gradient_dot, expected.gradient_dot);
|
||||
same_bits(scalar.weighted_geometric, expected.weighted_geometric);
|
||||
for (std::size_t component = 0; component < 3; ++component)
|
||||
same_bits(selected.accumulators[component], baseline.accumulators[component]);
|
||||
}
|
||||
|
||||
TEST(Hex8HighLow, GeometryPacketPreservesAsymmetricLanesAndUniformShapes) {
|
||||
if (fesa::hex8_internal::SelectMaterialPacketEvaluator() ==
|
||||
fesa::hex8_internal::EvaluateMaterialPacketScalar)
|
||||
GTEST_SKIP() << "Geometry AVX2 masked environment is not selected.";
|
||||
RecordProperty("private_geometry_packet_backend", "avx2");
|
||||
static_assert(std::is_trivial_v<fesa::hex8_internal::GeometryPacketInput>);
|
||||
static_assert(std::is_trivial_v<fesa::hex8_internal::GeometryPacketOutput>);
|
||||
std::size_t checks = 0;
|
||||
for (int shape = 0; shape < 4; ++shape) {
|
||||
auto input = GeometryDyadicFixture();
|
||||
for (std::size_t j = 0; j < 3; ++j) {
|
||||
if ((shape & 1) != 0) {
|
||||
input.gradient_a[j].low = std::ldexp(input.gradient_a[j].high, -55);
|
||||
for (std::size_t l = 0; l < 3; ++l)
|
||||
input.gradient_stress[j][l].low =
|
||||
std::ldexp(input.gradient_stress[j][l].high, -55);
|
||||
}
|
||||
if ((shape & 2) != 0)
|
||||
for (std::size_t lane = 0; lane < 4; ++lane)
|
||||
input.gradient_b[j].values[lane].low =
|
||||
std::ldexp(input.gradient_b[j].values[lane].high, -55);
|
||||
}
|
||||
ExpectGeometryPacketBitsAndFlags(input, false);
|
||||
ExpectGeometryPacketBitsAndFlags(input, true);
|
||||
checks += 2;
|
||||
}
|
||||
RecordProperty("avx2_geometry_uniform_bit_flag_checks", static_cast<int>(checks));
|
||||
}
|
||||
|
||||
TEST(Hex8HighLow, GeometryPacketRetainsSpecialLanesAndExactTailBoundary) {
|
||||
if (fesa::hex8_internal::SelectMaterialPacketEvaluator() ==
|
||||
fesa::hex8_internal::EvaluateMaterialPacketScalar)
|
||||
GTEST_SKIP() << "Geometry AVX2 masked environment is not selected.";
|
||||
using fesa::hex8_internal::PacketPair;
|
||||
const double tiny = std::numeric_limits<double>::denorm_min();
|
||||
const double maximum = std::numeric_limits<double>::max();
|
||||
const std::vector<PacketPair> special{{0, 0}, {-0.0, 0}, {1, -0.0}, {1, 1},
|
||||
{tiny, 0}, {maximum, maximum},
|
||||
{std::numeric_limits<double>::signaling_NaN(), 0},
|
||||
{0, std::numeric_limits<double>::signaling_NaN()}};
|
||||
std::size_t checks = 0;
|
||||
for (const auto pair : special)
|
||||
for (std::size_t lane = 0; lane < 4; ++lane) {
|
||||
auto input = GeometryDyadicFixture();
|
||||
input.gradient_b[1].values[lane] = pair;
|
||||
ExpectGeometryPacketBitsAndFlags(input, false);
|
||||
ExpectGeometryPacketBitsAndFlags(input, true);
|
||||
checks += 2;
|
||||
}
|
||||
const auto odd = [](int exponent) {
|
||||
return std::nextafter(std::ldexp(1.0, exponent),
|
||||
std::numeric_limits<double>::infinity());
|
||||
};
|
||||
for (int exponent : {-470, -471})
|
||||
for (std::size_t lane = 0; lane < 4; ++lane) {
|
||||
auto input = GeometryDyadicFixture();
|
||||
input.gradient_stress[0][0] = {odd(-500), 0};
|
||||
input.gradient_b[0].values[lane] = {odd(exponent), 0};
|
||||
ExpectGeometryPacketBitsAndFlags(input, false);
|
||||
checks++;
|
||||
}
|
||||
RecordProperty("avx2_geometry_special_tail_checks", static_cast<int>(checks));
|
||||
}
|
||||
|
||||
TEST(Hex8HighLow, GeometryPacketPreservesOrderedOverflowAndPreparedInvalid) {
|
||||
if (fesa::hex8_internal::SelectMaterialPacketEvaluator() ==
|
||||
fesa::hex8_internal::EvaluateMaterialPacketScalar)
|
||||
GTEST_SKIP() << "Geometry AVX2 masked environment is not selected.";
|
||||
const double maximum = std::numeric_limits<double>::max();
|
||||
std::size_t checks = 0;
|
||||
for (bool overflow_order : {false, true}) {
|
||||
SCOPED_TRACE(overflow_order);
|
||||
fesa::hex8_internal::GeometryPacketInput input{};
|
||||
input.weight = {0.5, 0};
|
||||
for (std::size_t l = 0; l < 3; ++l)
|
||||
for (std::size_t lane = 0; lane < 4; ++lane)
|
||||
input.gradient_b[l].values[lane] = {1, 0};
|
||||
input.gradient_stress[0][0] = {maximum, 0};
|
||||
input.gradient_stress[0][1] = {overflow_order ? maximum : -maximum, 0};
|
||||
input.gradient_stress[0][2] = {overflow_order ? -maximum : maximum, 0};
|
||||
ExpectGeometryPacketBitsAndFlags(input, false);
|
||||
ExpectGeometryPacketBitsAndFlags(input, true);
|
||||
checks += 2;
|
||||
}
|
||||
auto input = GeometryDyadicFixture();
|
||||
const auto invalid_first = fesa::high_low_original::Multiply(
|
||||
{std::ldexp(1.0, -600), 0}, {std::ldexp(1.0, -500), 0});
|
||||
input.gradient_stress[0][0] = {invalid_first.high, invalid_first.low};
|
||||
for (std::size_t lane = 0; lane < 4; ++lane)
|
||||
input.gradient_b[0].values[lane] = {std::ldexp(1.0, 600), 0};
|
||||
ExpectGeometryPacketBitsAndFlags(input, false);
|
||||
ExpectGeometryPacketBitsAndFlags(input, true);
|
||||
checks += 2;
|
||||
RecordProperty("avx2_geometry_ordered_invalid_checks", static_cast<int>(checks));
|
||||
}
|
||||
|
||||
TEST(Hex8HighLow, GeometryPacketSumFallbackPreservesNearMaxAndSubnormalStatus) {
|
||||
if (fesa::hex8_internal::SelectMaterialPacketEvaluator() ==
|
||||
fesa::hex8_internal::EvaluateMaterialPacketScalar)
|
||||
GTEST_SKIP() << "Geometry AVX2 masked environment is not selected.";
|
||||
const double maximum = std::numeric_limits<double>::max();
|
||||
const double normal = std::ldexp(1.0, -1022);
|
||||
const double tiny = std::ldexp(1.0, -1074);
|
||||
const double quarter = std::ldexp(1.0, 969);
|
||||
std::size_t checks = 0;
|
||||
for (double tail : {0.0, normal, tiny})
|
||||
for (std::size_t bad = 0; bad < 4; ++bad) {
|
||||
SCOPED_TRACE(tail);
|
||||
SCOPED_TRACE(bad);
|
||||
fesa::hex8_internal::GeometryPacketInput input{};
|
||||
input.weight = {0.5, 0};
|
||||
// Both pairs are normalized. Head sum is finite; middle contributes
|
||||
// 2^970 and the joined sum overflows. Other lanes retain finite values.
|
||||
input.gradient_stress[0][0] = {maximum, quarter};
|
||||
input.gradient_stress[0][1] = {quarter, tail};
|
||||
for (std::size_t lane = 0; lane < 4; ++lane) {
|
||||
const double scale = lane == bad ? 1.0 : 0.5;
|
||||
input.gradient_b[0].values[lane] = {scale, 0};
|
||||
input.gradient_b[1].values[lane] = {scale, 0};
|
||||
input.gradient_b[2].values[lane] = {1, 0};
|
||||
}
|
||||
ExpectGeometryPacketBitsAndFlags(input, false);
|
||||
ExpectGeometryPacketBitsAndFlags(input, true);
|
||||
checks += 2;
|
||||
}
|
||||
fesa::hex8_internal::GeometryPacketInput finite{};
|
||||
finite.weight = {1, 0};
|
||||
finite.gradient_stress[0][0] = {normal, 0};
|
||||
finite.gradient_stress[0][1] = {normal + tiny, 0};
|
||||
for (std::size_t lane = 0; lane < 4; ++lane) {
|
||||
finite.gradient_b[0].values[lane] = {1, 0};
|
||||
finite.gradient_b[1].values[lane] = {1, 0};
|
||||
}
|
||||
// TwoSum(N,N+d) has finite normal inputs and a subnormal error d.
|
||||
ExpectGeometryPacketBitsAndFlags(finite, false);
|
||||
ExpectGeometryPacketBitsAndFlags(finite, true);
|
||||
checks += 2;
|
||||
// Mixed prefix: finite subnormal-error lanes run before another lane's head
|
||||
// overflow. The bridge must preserve the whole packet's status union.
|
||||
for (std::size_t bad = 0; bad < 4; ++bad) {
|
||||
SCOPED_TRACE(bad);
|
||||
fesa::hex8_internal::GeometryPacketInput mixed{};
|
||||
mixed.weight = {1, 0};
|
||||
mixed.gradient_stress[0][2] = {normal, 0};
|
||||
mixed.gradient_stress[1][2] = {normal + tiny, 0};
|
||||
mixed.gradient_stress[2][0] = {maximum, 0};
|
||||
mixed.gradient_stress[2][1] = {maximum, 0};
|
||||
for (std::size_t lane = 0; lane < 4; ++lane) {
|
||||
mixed.gradient_b[0].values[lane] = {lane == bad ? 1.0 : 0.0, 0};
|
||||
mixed.gradient_b[1].values[lane] = {lane == bad ? 1.0 : 0.0, 0};
|
||||
mixed.gradient_b[2].values[lane] = {lane == bad ? 0.0 : 1.0, 0};
|
||||
}
|
||||
ExpectGeometryPacketBitsAndFlags(mixed, false);
|
||||
ExpectGeometryPacketBitsAndFlags(mixed, true);
|
||||
checks += 2;
|
||||
}
|
||||
RecordProperty("avx2_geometry_sum_fallback_checks", static_cast<int>(checks));
|
||||
}
|
||||
#endif
|
||||
|
||||
TEST(Hex8HighLow, PacketBackendSelectionRecoversAfterEnvironmentRestoration) {
|
||||
const auto initial = fesa::hex8_internal::SelectMaterialPacketEvaluator();
|
||||
const int rounding = std::fegetround();
|
||||
ASSERT_EQ(std::fesetround(FE_UPWARD), 0);
|
||||
EXPECT_EQ(fesa::hex8_internal::SelectMaterialPacketEvaluator(),
|
||||
fesa::hex8_internal::EvaluateMaterialPacketScalar);
|
||||
EXPECT_EQ(std::fesetround(rounding), 0);
|
||||
#if defined(_M_X64) || defined(__SSE2__)
|
||||
const auto control = _mm_getcsr();
|
||||
_mm_setcsr(control | 0x8040U);
|
||||
EXPECT_EQ(fesa::hex8_internal::SelectMaterialPacketEvaluator(),
|
||||
fesa::hex8_internal::EvaluateMaterialPacketScalar);
|
||||
_mm_setcsr(control);
|
||||
_mm_setcsr(control & ~0x80U);
|
||||
const auto unmasked = fesa::hex8_internal::SelectMaterialPacketEvaluator();
|
||||
_mm_setcsr(control);
|
||||
EXPECT_EQ(unmasked, fesa::hex8_internal::EvaluateMaterialPacketScalar);
|
||||
#endif
|
||||
EXPECT_EQ(fesa::hex8_internal::SelectMaterialPacketEvaluator(), initial);
|
||||
}
|
||||
|
||||
TEST(Hex8HighLow, PacketScalarBridgesPreserveOriginalRawBits) {
|
||||
using fesa::hex8_internal::PacketPair;
|
||||
using fesa::hex8_internal::PairPacket;
|
||||
static_assert(std::is_trivial_v<PacketPair> &&
|
||||
std::is_standard_layout_v<PacketPair>);
|
||||
static_assert(std::is_trivial_v<PairPacket> &&
|
||||
std::is_standard_layout_v<PairPacket>);
|
||||
static_assert(std::is_trivial_v<fesa::hex8_internal::MaterialPacketInput>);
|
||||
const double tiny = std::numeric_limits<double>::denorm_min();
|
||||
const std::vector<PacketPair> pairs{{0, 0}, {-0.0, 0}, {0, -0.0},
|
||||
{1, -0.0}, {1, std::ldexp(1.0, -54)}, {tiny, 0}, {1, tiny},
|
||||
{std::numeric_limits<double>::max(), 0}, {1, 1},
|
||||
{std::numeric_limits<double>::infinity(), 0},
|
||||
{std::numeric_limits<double>::signaling_NaN(), 0}};
|
||||
for (const auto left : pairs)
|
||||
for (const auto right : pairs) {
|
||||
PairPacket a{{left, left, left, left}};
|
||||
PairPacket b{{right, right, right, right}};
|
||||
PairPacket result;
|
||||
const fesa::high_low_original::HighLow x{left.high, left.low};
|
||||
const fesa::high_low_original::HighLow y{right.high, right.low};
|
||||
const auto expect = [&](fesa::high_low_original::HighLow expected) {
|
||||
for (std::size_t lane = 0; lane < 4; ++lane) {
|
||||
EXPECT_EQ(PairBits(result.values[lane].high), PairBits(expected.high));
|
||||
EXPECT_EQ(PairBits(result.values[lane].low), PairBits(expected.low));
|
||||
}
|
||||
};
|
||||
fesa::hex8_internal::ScalarPacketAdd(a, b, &result);
|
||||
expect(fesa::high_low_original::Add(x, y));
|
||||
fesa::hex8_internal::ScalarPacketMultiply(a, b, &result);
|
||||
expect(fesa::high_low_original::Multiply(x, y));
|
||||
const double high_left[4]{left.high, left.high, left.high, left.high};
|
||||
const double high_right[4]{right.high, right.high, right.high, right.high};
|
||||
fesa::hex8_internal::ScalarPacketTwoProduct(high_left, high_right, &result);
|
||||
expect(fesa::high_low_original::TwoProduct(left.high, right.high));
|
||||
}
|
||||
}
|
||||
|
||||
TEST(Hex8HighLow, PacketCapabilityRejectsMissingIntegerIsaAndOsState) {
|
||||
constexpr std::uint32_t leaf1 =
|
||||
(1U << 12) | (1U << 26) | (1U << 27) | (1U << 28);
|
||||
constexpr std::uint32_t leaf7 = (1U << 3) | (1U << 5) | (1U << 8);
|
||||
EXPECT_TRUE(fesa::hex8_internal::SupportsMaterialPacketInstructions(
|
||||
leaf1, 6, leaf7));
|
||||
for (const auto missing : {1U << 3, 1U << 5, 1U << 8})
|
||||
EXPECT_FALSE(fesa::hex8_internal::SupportsMaterialPacketInstructions(
|
||||
leaf1, 6, leaf7 & ~missing));
|
||||
for (const auto missing : {1U << 12, 1U << 26, 1U << 27, 1U << 28})
|
||||
EXPECT_FALSE(fesa::hex8_internal::SupportsMaterialPacketInstructions(
|
||||
leaf1 & ~missing, 6, leaf7));
|
||||
for (std::uint64_t state : {0ULL, 2ULL, 4ULL})
|
||||
EXPECT_FALSE(fesa::hex8_internal::SupportsMaterialPacketInstructions(
|
||||
leaf1, state, leaf7));
|
||||
}
|
||||
|
||||
TEST(Hex8HighLow, PacketDoesNotClearPriorMaskedStickyFlags) {
|
||||
std::fenv_t original;
|
||||
ASSERT_EQ(std::fegetenv(&original), 0);
|
||||
const auto evaluator = fesa::hex8_internal::SelectMaterialPacketEvaluator();
|
||||
ASSERT_EQ(std::feraiseexcept(FE_INEXACT), 0);
|
||||
fesa::hex8_internal::MaterialPacketInput input{};
|
||||
input.weight = {1};
|
||||
for (std::size_t lane = 0; lane < 4; ++lane) {
|
||||
input.deviatoric_left.values[lane] = {1, std::ldexp(1.0, -54)};
|
||||
input.deviatoric_right.values[lane] = {2, std::ldexp(1.0, -54)};
|
||||
}
|
||||
fesa::hex8_internal::PairPacket output;
|
||||
evaluator(input, &output);
|
||||
const bool preserved = (std::fetestexcept(FE_INEXACT) & FE_INEXACT) != 0;
|
||||
EXPECT_EQ(std::fesetenv(&original), 0);
|
||||
EXPECT_TRUE(preserved);
|
||||
}
|
||||
|
||||
fesa::Hex8Element UnitBrick(double offset = 0, double nu = 0) {
|
||||
fesa::ElementDofLayout layout;
|
||||
layout.node_indices = {0, 1, 2, 3, 4, 5, 6, 7};
|
||||
@@ -27,6 +847,116 @@ fesa::Hex8Element UnitBrick(double offset = 0, double nu = 0) {
|
||||
return fesa::Hex8Element::Create(0, layout, coordinates, material, 2).Value();
|
||||
}
|
||||
|
||||
void ExpectSamePairResponse(const fesa::Hex8HighLowResponse& actual,
|
||||
const fesa::Hex8HighLowResponse& expected) {
|
||||
EXPECT_EQ(PairBits(actual.high.strain_energy),
|
||||
PairBits(expected.high.strain_energy));
|
||||
EXPECT_EQ(PairBits(actual.strain_energy_low),
|
||||
PairBits(expected.strain_energy_low));
|
||||
ASSERT_EQ(actual.high.tangent.Rows(), 24U);
|
||||
ASSERT_EQ(actual.tangent_low.Rows(), 24U);
|
||||
for (std::size_t i = 0; i < 24; ++i) {
|
||||
EXPECT_EQ(PairBits(actual.high.internal_force[i]),
|
||||
PairBits(expected.high.internal_force[i]));
|
||||
EXPECT_EQ(PairBits(actual.internal_force_low[i]),
|
||||
PairBits(expected.internal_force_low[i]));
|
||||
for (std::size_t j = 0; j < 24; ++j) {
|
||||
EXPECT_EQ(PairBits(actual.high.tangent(i, j)),
|
||||
PairBits(expected.high.tangent(i, j)));
|
||||
EXPECT_EQ(PairBits(actual.tangent_low(i, j)),
|
||||
PairBits(expected.tangent_low(i, j)));
|
||||
}
|
||||
}
|
||||
for (std::size_t point = 0; point < 8; ++point) {
|
||||
EXPECT_EQ(actual.high.points[point].integration_point,
|
||||
expected.high.points[point].integration_point);
|
||||
for (std::size_t i = 0; i < 6; ++i) {
|
||||
EXPECT_EQ(PairBits(actual.high.points[point].cauchy_stress[i]),
|
||||
PairBits(expected.high.points[point].cauchy_stress[i]));
|
||||
EXPECT_EQ(PairBits(actual.high.points[point].strain[i]),
|
||||
PairBits(expected.high.points[point].strain[i]));
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
TEST(Hex8HighLow, ConcurrentFirstLinearTrialsAcrossCopiesAndMoveKeepBits) {
|
||||
const auto element = UnitBrick();
|
||||
auto copied = element;
|
||||
const auto moved = std::move(copied);
|
||||
fesa::Vector high(24), low_a(24), low_b(24);
|
||||
for (std::size_t i = 0; i < 24; ++i) high[i] = 1;
|
||||
for (auto a : {1, 2, 5, 6}) {
|
||||
low_a[3U * a] = std::ldexp(1.0, -60);
|
||||
low_b[3U * a] = -std::ldexp(1.0, -59);
|
||||
}
|
||||
const auto oracle = UnitBrick();
|
||||
const auto expected_a = oracle.EvaluateLinearHighLow(high, low_a);
|
||||
const auto expected_b = oracle.EvaluateLinearHighLow(high, low_b);
|
||||
ASSERT_TRUE(expected_a.HasValue());
|
||||
ASSERT_TRUE(expected_b.HasValue());
|
||||
std::promise<void> start;
|
||||
const auto signal = start.get_future().share();
|
||||
std::atomic<std::size_t> arrived{0U};
|
||||
std::array<std::future<fesa::Result<fesa::Hex8HighLowResponse>>, 4> calls;
|
||||
for (std::size_t i = 0; i < calls.size(); ++i)
|
||||
calls[i] = std::async(std::launch::async, [&, i] {
|
||||
arrived.fetch_add(1U, std::memory_order_release);
|
||||
signal.wait();
|
||||
return (i % 2U == 0U ? element : moved)
|
||||
.EvaluateLinearHighLow(high, i < 2U ? low_a : low_b);
|
||||
});
|
||||
while (arrived.load(std::memory_order_acquire) != calls.size())
|
||||
std::this_thread::yield();
|
||||
start.set_value();
|
||||
for (std::size_t i = 0; i < calls.size(); ++i) {
|
||||
const auto response = calls[i].get();
|
||||
ASSERT_TRUE(response.HasValue());
|
||||
ExpectSamePairResponse(response.Value(),
|
||||
i < 2U ? expected_a.Value() : expected_b.Value());
|
||||
}
|
||||
}
|
||||
|
||||
TEST(Hex8HighLow, FirstLinearPreparationRecoversAfterTrialAndEnvironmentFailure) {
|
||||
ASSERT_TRUE(fesa::math_internal::ArithmeticEnvironmentSupported());
|
||||
const auto element = UnitBrick();
|
||||
fesa::Vector high(24), low(24);
|
||||
EXPECT_FALSE(element.EvaluateLinearHighLow(fesa::Vector(23), low).HasValue());
|
||||
high[0] = std::numeric_limits<double>::infinity();
|
||||
EXPECT_FALSE(element.EvaluateLinearHighLow(high, low).HasValue());
|
||||
high[0] = 0;
|
||||
struct RestoreEnvironment {
|
||||
int rounding = std::fegetround();
|
||||
#if defined(_M_X64) || defined(__SSE2__)
|
||||
unsigned csr = _mm_getcsr();
|
||||
#endif
|
||||
~RestoreEnvironment() {
|
||||
std::fesetround(rounding);
|
||||
#if defined(_M_X64) || defined(__SSE2__)
|
||||
_mm_setcsr(csr);
|
||||
#endif
|
||||
}
|
||||
} restore;
|
||||
ASSERT_EQ(std::fesetround(FE_DOWNWARD), 0);
|
||||
const auto bad_environment = element.EvaluateLinearHighLow(high, low);
|
||||
ASSERT_FALSE(bad_environment.HasValue());
|
||||
EXPECT_EQ(bad_environment.GetStatus().Diagnostics()[0].message,
|
||||
"Hex8 high+low requires nearest rounding and gradual underflow.");
|
||||
ASSERT_EQ(std::fesetround(FE_TONEAREST), 0);
|
||||
#if defined(_M_X64) || defined(__SSE2__)
|
||||
_mm_setcsr(restore.csr | 0x8040U);
|
||||
EXPECT_FALSE(element.EvaluateLinearHighLow(high, low).HasValue());
|
||||
_mm_setcsr(restore.csr);
|
||||
#endif
|
||||
const auto recovered = element.EvaluateLinearHighLow(high, low);
|
||||
ASSERT_TRUE(recovered.HasValue());
|
||||
high[3] = -2;
|
||||
EXPECT_FALSE(element.EvaluateLinearHighLow(high, low).HasValue());
|
||||
high[3] = 0;
|
||||
const auto after_failure = element.EvaluateLinearHighLow(high, low);
|
||||
ASSERT_TRUE(after_failure.HasValue());
|
||||
ExpectSamePairResponse(after_failure.Value(), recovered.Value());
|
||||
}
|
||||
|
||||
TEST(Hex8HighLow, LowOnlyAffineStrainSurvivesUniformHighTranslation) {
|
||||
auto brick = UnitBrick();
|
||||
fesa::Vector high(24), low(24);
|
||||
|
||||
@@ -4,6 +4,7 @@
|
||||
#include <gtest/gtest.h>
|
||||
|
||||
#include <array>
|
||||
#include <cmath>
|
||||
#include <cstddef>
|
||||
#include <limits>
|
||||
#include <stdexcept>
|
||||
@@ -426,3 +427,266 @@ TEST(JetLinearSolve, FailedChannelSolvePreservesCandidateAndInputs) {
|
||||
}
|
||||
} // namespace
|
||||
} // namespace fesa::math_internal
|
||||
|
||||
namespace fesa::dense_blas_internal {
|
||||
TEST(DenseBlasInternal, DiagonalProductKeepsEntrywiseCancellationAndChecks) {
|
||||
Vector diagonal{3U};
|
||||
diagonal[0U] = 4;
|
||||
diagonal[1U] = 2;
|
||||
diagonal[2U] = -1;
|
||||
Vector input{3U};
|
||||
const double large = std::ldexp(1.0, 56);
|
||||
input[0U] = 1;
|
||||
input[1U] = -large;
|
||||
input[2U] = 2 * large;
|
||||
const auto product = MultiplyDiagonal(diagonal, input);
|
||||
EXPECT_DOUBLE_EQ(product[0U] + (product[1U] - product[2U]), 4);
|
||||
EXPECT_EQ(MultiplyDiagonal(Vector{0U}, Vector{0U}).Size(), 0U);
|
||||
EXPECT_THROW(static_cast<void>(MultiplyDiagonal(diagonal, Vector{2U})),
|
||||
std::invalid_argument);
|
||||
input[0U] = std::numeric_limits<double>::infinity();
|
||||
EXPECT_THROW(static_cast<void>(MultiplyDiagonal(diagonal, input)),
|
||||
std::invalid_argument);
|
||||
input[0U] = 1;
|
||||
diagonal[0U] = std::numeric_limits<double>::quiet_NaN();
|
||||
EXPECT_THROW(static_cast<void>(MultiplyDiagonal(diagonal, input)),
|
||||
std::invalid_argument);
|
||||
}
|
||||
|
||||
TEST(DenseBlasInternal, LocalDenseScopeRestoresTlsAfterProductsAndUnwind) {
|
||||
const int previous = mkl_set_num_threads_local(0);
|
||||
struct Restore {
|
||||
int previous;
|
||||
~Restore() { static_cast<void>(mkl_set_num_threads_local(previous)); }
|
||||
} restore{previous};
|
||||
const int default_threads = mkl_get_max_threads();
|
||||
const std::array<double, 2U> left{0.0, 2.0};
|
||||
const std::array<double, 2U> right{3.0, 4.0};
|
||||
std::array<double, 4U> product{};
|
||||
product.fill(std::numeric_limits<double>::quiet_NaN());
|
||||
{
|
||||
const ScopedLocalDenseThreads scope{};
|
||||
EXPECT_EQ(mkl_get_max_threads(), 1);
|
||||
EXPECT_TRUE(
|
||||
OuterProduct(left.data(), 2U, right.data(), 2U, product.data()));
|
||||
EXPECT_DOUBLE_EQ(product[0U], 0.0);
|
||||
EXPECT_DOUBLE_EQ(product[3U], 8.0);
|
||||
}
|
||||
EXPECT_EQ(mkl_get_max_threads(), default_threads);
|
||||
EXPECT_EQ(mkl_set_num_threads_local(0), 0);
|
||||
try {
|
||||
const ScopedLocalDenseThreads scope{};
|
||||
OuterProduct(nullptr, 2U, right.data(), 2U, product.data());
|
||||
} catch (const std::invalid_argument&) {
|
||||
}
|
||||
EXPECT_EQ(mkl_set_num_threads_local(0), 0);
|
||||
static_cast<void>(mkl_set_num_threads_local(3));
|
||||
{
|
||||
const ScopedLocalDenseThreads scope{};
|
||||
EXPECT_EQ(mkl_get_max_threads(), 3);
|
||||
}
|
||||
EXPECT_EQ(mkl_get_max_threads(), 3);
|
||||
}
|
||||
|
||||
TEST(DenseBlasInternal, OuterProductLeavesFiniteInputOverflowForOwnerGate) {
|
||||
const std::array<double, 1U> left{std::numeric_limits<double>::max()};
|
||||
const std::array<double, 1U> right{2.0};
|
||||
std::array<double, 1U> product{};
|
||||
EXPECT_TRUE(OuterProduct(left.data(), 1U, right.data(), 1U, product.data()));
|
||||
EXPECT_TRUE(std::isinf(product[0U]));
|
||||
}
|
||||
|
||||
TEST(DenseBlasInternal,
|
||||
OuterProductUsesRectangularStorageAndPreservesRejection) {
|
||||
const std::array<double, 2U> left{2.0, -3.0};
|
||||
const std::array<double, 3U> right{4.0, -5.0, 0.25};
|
||||
std::array<double, 6U> product{};
|
||||
ASSERT_TRUE(OuterProduct(left.data(), left.size(), right.data(), right.size(),
|
||||
product.data()));
|
||||
const std::array<double, 6U> expected{8.0, -10.0, 0.5, -12.0, 15.0, -0.75};
|
||||
EXPECT_EQ(product, expected);
|
||||
const auto accepted = product;
|
||||
const std::array<double, 2U> invalid{
|
||||
1.0, std::numeric_limits<double>::quiet_NaN()};
|
||||
EXPECT_FALSE(OuterProduct(invalid.data(), invalid.size(), right.data(),
|
||||
right.size(), product.data()));
|
||||
EXPECT_EQ(product, accepted);
|
||||
EXPECT_TRUE(OuterProduct(nullptr, 0U, nullptr, 3U, nullptr));
|
||||
EXPECT_TRUE(OuterProduct(nullptr, 2U, nullptr, 0U, nullptr));
|
||||
EXPECT_THROW(OuterProduct(nullptr, 2U, right.data(), 3U, product.data()),
|
||||
std::invalid_argument);
|
||||
const auto too_large =
|
||||
static_cast<std::size_t>((std::numeric_limits<MKL_INT>::max)()) + 1U;
|
||||
EXPECT_THROW(OuterProduct(nullptr, too_large, nullptr, 1U, nullptr),
|
||||
std::length_error);
|
||||
const auto too_many_elements =
|
||||
std::numeric_limits<std::size_t>::max() / sizeof(double) + 1U;
|
||||
EXPECT_THROW(OuterProduct(nullptr, too_many_elements, nullptr, 1U, nullptr),
|
||||
std::length_error);
|
||||
}
|
||||
|
||||
TEST(DenseBlasInternal, PolicyQueryPreservesDefaultPositiveAndNestedTls) {
|
||||
const int previous = mkl_set_num_threads_local(0);
|
||||
struct Restore {
|
||||
int previous;
|
||||
~Restore() { static_cast<void>(mkl_set_num_threads_local(previous)); }
|
||||
} restore{previous};
|
||||
const int global = mkl_get_max_threads();
|
||||
const int domain = mkl_domain_get_max_threads(MKL_DOMAIN_BLAS);
|
||||
const int dynamic = mkl_get_dynamic();
|
||||
for (int repeat = 0; repeat < 2; ++repeat) {
|
||||
const auto policy = ReadScopedLocalDensePolicy();
|
||||
EXPECT_EQ(policy.blas_max_threads, 1);
|
||||
EXPECT_EQ(policy.dynamic, dynamic);
|
||||
EXPECT_EQ(mkl_set_num_threads_local(0), 0);
|
||||
EXPECT_EQ(mkl_get_max_threads(), global);
|
||||
EXPECT_EQ(mkl_domain_get_max_threads(MKL_DOMAIN_BLAS), domain);
|
||||
EXPECT_EQ(mkl_get_dynamic(), dynamic);
|
||||
}
|
||||
static_cast<void>(mkl_set_num_threads_local(2));
|
||||
EXPECT_EQ(ReadScopedLocalDensePolicy().blas_max_threads, 2);
|
||||
EXPECT_EQ(mkl_set_num_threads_local(2), 2);
|
||||
static_cast<void>(mkl_set_num_threads_local(0));
|
||||
try {
|
||||
const ScopedLocalDenseThreads outer{};
|
||||
EXPECT_EQ(ReadScopedLocalDensePolicy().blas_max_threads, 1);
|
||||
EXPECT_EQ(mkl_set_num_threads_local(1), 1);
|
||||
throw std::runtime_error{"policy-query-unwind"};
|
||||
} catch (const std::runtime_error&) {
|
||||
}
|
||||
EXPECT_EQ(mkl_set_num_threads_local(0), 0);
|
||||
EXPECT_EQ(mkl_get_dynamic(), dynamic);
|
||||
}
|
||||
|
||||
TEST(DenseBlasInternal, SingleEquationScopeRestoresTlsAndRespectsOverrides) {
|
||||
const int previous = mkl_set_num_threads_local(0);
|
||||
struct Restore {
|
||||
int previous;
|
||||
~Restore() { static_cast<void>(mkl_set_num_threads_local(previous)); }
|
||||
} restore{previous};
|
||||
const int default_threads = mkl_get_max_threads();
|
||||
{
|
||||
const ScopedSingleEquationThreads scope{1U};
|
||||
EXPECT_EQ(mkl_get_max_threads(), 1);
|
||||
}
|
||||
EXPECT_EQ(mkl_get_max_threads(), default_threads);
|
||||
EXPECT_EQ(mkl_set_num_threads_local(0), 0);
|
||||
{
|
||||
const ScopedSingleEquationThreads scope{2U};
|
||||
EXPECT_EQ(mkl_get_max_threads(), default_threads);
|
||||
}
|
||||
try {
|
||||
const ScopedSingleEquationThreads scope{1U};
|
||||
throw std::runtime_error{"scope failure"};
|
||||
} catch (const std::runtime_error&) {
|
||||
}
|
||||
EXPECT_EQ(mkl_set_num_threads_local(0), 0);
|
||||
static_cast<void>(mkl_set_num_threads_local(3));
|
||||
{
|
||||
const ScopedSingleEquationThreads scope{1U};
|
||||
EXPECT_EQ(mkl_get_max_threads(), 3);
|
||||
}
|
||||
EXPECT_EQ(mkl_get_max_threads(), 3);
|
||||
}
|
||||
|
||||
TEST(DenseBlasInternal, TransposeProductChecksShapeAndKnownRectangularAction) {
|
||||
Matrix left{3U, 2U};
|
||||
Matrix right{3U, 1U};
|
||||
for (std::size_t row = 0; row < 3U; ++row) {
|
||||
left(row, 0U) = static_cast<double>(row + 1U);
|
||||
left(row, 1U) = 2.0;
|
||||
right(row, 0U) = static_cast<double>(row);
|
||||
}
|
||||
const auto product = MultiplyTransposeLeft(left, right);
|
||||
ASSERT_EQ(product.Rows(), 2U);
|
||||
ASSERT_EQ(product.Columns(), 1U);
|
||||
EXPECT_DOUBLE_EQ(product(0U, 0U), 8.0);
|
||||
EXPECT_DOUBLE_EQ(product(1U, 0U), 6.0);
|
||||
EXPECT_THROW(static_cast<void>(MultiplyTransposeLeft(left, Matrix{2U, 1U})),
|
||||
std::invalid_argument);
|
||||
const auto empty = MultiplyTransposeLeft(Matrix{0U, 2U}, Matrix{0U, 3U});
|
||||
EXPECT_EQ(empty.Rows(), 2U);
|
||||
EXPECT_EQ(empty.Columns(), 3U);
|
||||
EXPECT_DOUBLE_EQ(empty(1U, 2U), 0.0);
|
||||
left(0U, 0U) = std::numeric_limits<double>::quiet_NaN();
|
||||
EXPECT_THROW(static_cast<void>(MultiplyTransposeLeft(left, right)),
|
||||
std::invalid_argument);
|
||||
left(0U, 0U) = 1.0;
|
||||
right(0U, 0U) = std::numeric_limits<double>::infinity();
|
||||
EXPECT_THROW(static_cast<void>(MultiplyTransposeLeft(left, right)),
|
||||
std::invalid_argument);
|
||||
}
|
||||
|
||||
TEST(DenseBlasInternal, TransposeRightProductUsesInnerAndRectangularStrides) {
|
||||
const std::array<double, 6U> left{1, 2, 3, 4, 5, 6};
|
||||
const std::array<double, 12U> right{7, 8, 9, 10, 11, 12,
|
||||
13, 14, 15, 16, 17, 18};
|
||||
std::array<double, 8U> product;
|
||||
ASSERT_TRUE(MultiplyTransposeRight(left.data(), 2U, right.data(), 4U, 3U,
|
||||
product.data()));
|
||||
const std::array<double, 8U> expected{50, 68, 86, 104, 122, 167, 212, 257};
|
||||
EXPECT_EQ(product, expected);
|
||||
EXPECT_TRUE(
|
||||
MultiplyTransposeRight(nullptr, 2U, nullptr, 4U, 0U, product.data()));
|
||||
for (const auto value : product) EXPECT_DOUBLE_EQ(value, 0.0);
|
||||
auto nonfinite = right;
|
||||
nonfinite[8U] = std::numeric_limits<double>::infinity();
|
||||
product.fill(31.0);
|
||||
EXPECT_FALSE(MultiplyTransposeRight(left.data(), 2U, nonfinite.data(), 4U, 3U,
|
||||
product.data()));
|
||||
for (const auto value : product) EXPECT_DOUBLE_EQ(value, 31.0);
|
||||
}
|
||||
|
||||
// The former lower/inverse output parameters are now owned factor results.
|
||||
TEST(DenseBlasInternal, CholeskyAndInverseMatchKnownFactorsAndKeepFailedOutput) {
|
||||
Matrix matrix{2U, 2U};
|
||||
matrix(0, 0) = 4;
|
||||
matrix(0, 1) = matrix(1, 0) = 2;
|
||||
matrix(1, 1) = 5;
|
||||
auto factor = DenseFactor::Cholesky(matrix);
|
||||
ASSERT_TRUE(factor.HasValue());
|
||||
const auto lower = factor.Value().Lower();
|
||||
Matrix identity{2U, 2U};
|
||||
identity(0, 0) = identity(1, 1) = 1;
|
||||
const auto inverse = factor.Value().SolveLower(identity);
|
||||
ASSERT_TRUE(lower.HasValue());
|
||||
ASSERT_TRUE(inverse.HasValue());
|
||||
EXPECT_DOUBLE_EQ(lower.Value()(0, 0), 2);
|
||||
EXPECT_DOUBLE_EQ(lower.Value()(1, 0), 1);
|
||||
EXPECT_DOUBLE_EQ(lower.Value()(1, 1), 2);
|
||||
EXPECT_DOUBLE_EQ(lower.Value()(0, 1), 0);
|
||||
EXPECT_DOUBLE_EQ(inverse.Value()(0, 0), .5);
|
||||
EXPECT_DOUBLE_EQ(inverse.Value()(1, 0), -.25);
|
||||
EXPECT_DOUBLE_EQ(inverse.Value()(1, 1), .5);
|
||||
matrix(1, 1) = 0;
|
||||
EXPECT_FALSE(DenseFactor::Cholesky(matrix).HasValue());
|
||||
EXPECT_DOUBLE_EQ(lower.Value()(1, 1), 2);
|
||||
EXPECT_DOUBLE_EQ(inverse.Value()(1, 1), .5);
|
||||
EXPECT_FALSE(DenseFactor::Cholesky(Matrix{2U, 1U}).HasValue());
|
||||
matrix(0, 0) = std::numeric_limits<double>::quiet_NaN();
|
||||
EXPECT_FALSE(DenseFactor::Cholesky(matrix).HasValue());
|
||||
EXPECT_DOUBLE_EQ(factor.Value().SolveLower(identity).Value()(1, 1), .5);
|
||||
}
|
||||
|
||||
TEST(DenseBlasInternal,
|
||||
CholeskyFailureReasonPreservesCandidatesAndResetsOnReuse) {
|
||||
Matrix matrix{2U, 2U};
|
||||
matrix(0, 0) = 4;
|
||||
matrix(1, 1) = 9;
|
||||
const auto accepted = DenseFactor::Cholesky(matrix);
|
||||
ASSERT_TRUE(accepted.HasValue());
|
||||
Matrix identity{2U, 2U};
|
||||
identity(0, 0) = identity(1, 1) = 1;
|
||||
matrix(1, 1) = -1;
|
||||
const auto failed = DenseFactor::Cholesky(matrix);
|
||||
ASSERT_FALSE(failed.HasValue());
|
||||
ASSERT_FALSE(failed.GetStatus().Diagnostics().empty());
|
||||
EXPECT_EQ(failed.GetStatus().Diagnostics()[0].code, "dense-factor-pivot");
|
||||
EXPECT_DOUBLE_EQ(accepted.Value().Lower().Value()(1, 1), 3);
|
||||
EXPECT_DOUBLE_EQ(accepted.Value().SolveLower(identity).Value()(1, 1), 1.0 / 3.0);
|
||||
matrix(1, 1) = 9;
|
||||
EXPECT_TRUE(DenseFactor::Cholesky(matrix).HasValue());
|
||||
EXPECT_FALSE(DenseFactor::Cholesky(Matrix{2U, 1U}).HasValue());
|
||||
EXPECT_TRUE(DenseFactor::Cholesky(matrix).HasValue());
|
||||
}
|
||||
} // namespace fesa::dense_blas_internal
|
||||
|
||||
@@ -1,10 +1,16 @@
|
||||
#include "../../../src/fesa/math/high_low_arithmetic.h"
|
||||
#include "elements/hex8_pair_simd.h"
|
||||
|
||||
#include <gtest/gtest.h>
|
||||
#include "elements/hex8_pair_simd.h"
|
||||
|
||||
#include <cmath>
|
||||
#include <cstdint>
|
||||
#include <cstring>
|
||||
#include <limits>
|
||||
#include <random>
|
||||
#include <vector>
|
||||
|
||||
#include "high_low_arithmetic_original.h"
|
||||
|
||||
namespace {
|
||||
using namespace fesa::math_internal;
|
||||
@@ -126,9 +132,111 @@ TEST(HighLowArithmetic, RejectsChangedRoundingAndFlushToZeroEnvironment) {
|
||||
EXPECT_FALSE(ArithmeticEnvironmentSupported());
|
||||
#endif
|
||||
}
|
||||
} // namespace
|
||||
|
||||
namespace {
|
||||
std::uint64_t Bits(const double value) {
|
||||
std::uint64_t result = 0;
|
||||
std::memcpy(&result, &value, sizeof(result));
|
||||
return result;
|
||||
}
|
||||
|
||||
double FromBits(const std::uint64_t bits) {
|
||||
double result = 0;
|
||||
std::memcpy(&result, &bits, sizeof(result));
|
||||
return result;
|
||||
}
|
||||
|
||||
TEST(HighLowArithmetic, FiniteClassificationMatchesBinary64Boundaries) {
|
||||
const auto check = [](const double value) {
|
||||
const bool expected = std::isfinite(value);
|
||||
EXPECT_EQ(IsFinite(HighLow{value, 0.0}), expected);
|
||||
EXPECT_EQ(IsFinite(HighLow{1.0, value}), expected);
|
||||
};
|
||||
for (std::uint64_t exponent = 0; exponent < 2048U; ++exponent) {
|
||||
for (const auto fraction : {0ULL, 1ULL, 1ULL << 51U,
|
||||
(1ULL << 52U) - 1ULL}) {
|
||||
for (const auto sign : {0ULL, 1ULL << 63U})
|
||||
check(FromBits(sign | (exponent << 52U) | fraction));
|
||||
}
|
||||
}
|
||||
std::mt19937_64 random{0x5800f17U};
|
||||
for (int sample = 0; sample < 10000; ++sample) check(FromBits(random()));
|
||||
}
|
||||
|
||||
void ExpectSamePair(const HighLow actual,
|
||||
const fesa::high_low_original::HighLow expected) {
|
||||
EXPECT_EQ(Bits(actual.high), Bits(expected.high));
|
||||
EXPECT_EQ(Bits(actual.low), Bits(expected.low));
|
||||
}
|
||||
|
||||
TEST(HighLowArithmetic, BitExponentMatchesFrozenOracleAcrossEveryExponent) {
|
||||
ASSERT_TRUE(ArithmeticEnvironmentSupported());
|
||||
// Every normal exponent, every possible trailing significand-bit count,
|
||||
// both signs; then every subnormal single-bit and mixed-bit boundary.
|
||||
for (std::uint64_t exponent = 1; exponent < 2047; ++exponent) {
|
||||
for (unsigned trailing = 0; trailing <= 52U; ++trailing) {
|
||||
const auto fraction = trailing == 52U ? 0ULL : 1ULL << trailing;
|
||||
for (const auto sign : {0ULL, 1ULL << 63U}) {
|
||||
const double value = FromBits(sign | (exponent << 52U) | fraction);
|
||||
ASSERT_EQ(LowestBitExponent(value),
|
||||
fesa::high_low_original::LowestBitExponent(value));
|
||||
}
|
||||
}
|
||||
}
|
||||
for (unsigned bit = 0; bit < 52U; ++bit) {
|
||||
for (const auto significand : {1ULL << bit, (1ULL << 52U) - (1ULL << bit)}) {
|
||||
const double value = FromBits(significand);
|
||||
EXPECT_EQ(LowestBitExponent(value),
|
||||
fesa::high_low_original::LowestBitExponent(value));
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
TEST(HighLowArithmetic, OptimizedArithmeticMatchesFrozenOriginalBits) {
|
||||
ASSERT_TRUE(ArithmeticEnvironmentSupported());
|
||||
std::vector<double> values{0.0, -0.0,
|
||||
std::numeric_limits<double>::denorm_min(),
|
||||
-std::numeric_limits<double>::denorm_min(),
|
||||
std::numeric_limits<double>::min(),
|
||||
std::nextafter(std::numeric_limits<double>::min(), 0.0),
|
||||
std::numeric_limits<double>::max(),
|
||||
-std::numeric_limits<double>::max(), 1.0, -1.0,
|
||||
std::nextafter(1.0, 2.0), std::ldexp(1.0, -53),
|
||||
std::ldexp(1.0, -54), std::numeric_limits<double>::infinity(),
|
||||
-std::numeric_limits<double>::infinity(),
|
||||
std::numeric_limits<double>::quiet_NaN()};
|
||||
std::mt19937_64 random{0x58a0fU};
|
||||
for (int sample = 0; sample < 4000; ++sample) {
|
||||
values.push_back(FromBits(random()));
|
||||
}
|
||||
for (std::size_t index = 0; index < values.size(); ++index) {
|
||||
const double high = values[index];
|
||||
const double low = values[(index * 13U + 7U) % values.size()];
|
||||
const fesa::high_low_original::HighLow original{high, low};
|
||||
EXPECT_EQ(IsNormalized({high, low}),
|
||||
fesa::high_low_original::IsNormalized(original));
|
||||
// Normalize a raw pair with the frozen operation, never the new predicate.
|
||||
const auto a = fesa::high_low_original::TwoSum(high, low);
|
||||
const auto b = fesa::high_low_original::TwoSum(
|
||||
values[(index + 1U) % values.size()],
|
||||
values[(index * 3U + 2U) % values.size()]);
|
||||
ExpectSamePair(Add({a.high, a.low}, {b.high, b.low}),
|
||||
fesa::high_low_original::Add(a, b));
|
||||
ExpectSamePair(Multiply({a.high, a.low}, {b.high, b.low}),
|
||||
fesa::high_low_original::Multiply(a, b));
|
||||
ExpectSamePair(Divide({a.high, a.low}, {b.high, b.low}),
|
||||
fesa::high_low_original::Divide(a, b));
|
||||
ExpectSamePair(TwoProduct(high, low),
|
||||
fesa::high_low_original::TwoProduct(high, low));
|
||||
}
|
||||
for (double high : {1.0, std::nextafter(1.0, 2.0), -1.0,
|
||||
std::numeric_limits<double>::max()}) {
|
||||
for (double low : {0.0, -0.0, std::ldexp(1.0, -53),
|
||||
-std::ldexp(1.0, -53)}) {
|
||||
EXPECT_EQ(IsNormalized({high, low}),
|
||||
fesa::high_low_original::IsNormalized({high, low}));
|
||||
}
|
||||
}
|
||||
}
|
||||
TEST(HighLowArithmetic, PacketDispatchRetainsComponentsAndInstructionGates) {
|
||||
using namespace fesa::hex8_internal;
|
||||
const std::uint32_t leaf1 = (1U << 12) | (1U << 26) | (1U << 27) | (1U << 28);
|
||||
|
||||
@@ -167,4 +167,21 @@ TEST(DenseMath, MatrixSelfAssignmentPreservesShapeAndStorage) {
|
||||
}
|
||||
|
||||
} // namespace
|
||||
TEST(DenseMath, MatrixProductsRejectNonfiniteOperandsAndPreserveValidReuse) {
|
||||
Matrix left{2U, 2U, 1.0};
|
||||
Matrix right{2U, 1U, 2.0};
|
||||
Vector rhs{2U, 2.0};
|
||||
rhs[1U] = std::numeric_limits<double>::infinity();
|
||||
EXPECT_THROW(static_cast<void>(left.Multiply(rhs)), std::invalid_argument);
|
||||
rhs[1U] = 2.0;
|
||||
left(0U, 1U) = std::numeric_limits<double>::quiet_NaN();
|
||||
EXPECT_THROW(static_cast<void>(left.Multiply(rhs)), std::invalid_argument);
|
||||
EXPECT_THROW(static_cast<void>(left.Multiply(right)), std::invalid_argument);
|
||||
left(0U, 1U) = 1.0;
|
||||
right(1U, 0U) = std::numeric_limits<double>::infinity();
|
||||
EXPECT_THROW(static_cast<void>(left.Multiply(right)), std::invalid_argument);
|
||||
right(1U, 0U) = 2.0;
|
||||
EXPECT_DOUBLE_EQ(left.Multiply(rhs)[0U], 4.0);
|
||||
EXPECT_DOUBLE_EQ(left.Multiply(right)(1U, 0U), 4.0);
|
||||
}
|
||||
} // namespace fesa
|
||||
|
||||
@@ -3,6 +3,8 @@
|
||||
#include <gtest/gtest.h>
|
||||
|
||||
#include <algorithm>
|
||||
#include <cmath>
|
||||
#include <future>
|
||||
#include <limits>
|
||||
#include <type_traits>
|
||||
#include <utility>
|
||||
@@ -131,4 +133,104 @@ TEST(SparseAssembly, PreservesExpectedStructuralZeros) {
|
||||
4);
|
||||
}
|
||||
|
||||
TEST(SparseAssembly, MultipliesRectangularCopyMoveAndConcurrentConstCalls) {
|
||||
auto assembled = SparseMatrix::FromCoo(
|
||||
3U, 5U, {{0U, 4U, 3.0, 0U, 0U}, {2U, 1U, -2.0, 1U, 0U}},
|
||||
{{0U, 1U, 1U, 2U}, {4U, 1U}});
|
||||
ASSERT_TRUE(assembled.HasValue());
|
||||
const auto original = assembled.Value();
|
||||
auto copied = original;
|
||||
auto moved = std::move(copied);
|
||||
Vector rhs{5U, 2.0};
|
||||
const auto evaluate = [&rhs](const SparseMatrix& matrix) {
|
||||
for (int repeat = 0; repeat < 20; ++repeat) {
|
||||
const auto product = matrix.Multiply(rhs);
|
||||
if (product.Size() != 3U || product[0U] != 6.0 ||
|
||||
product[1U] != 0.0 || product[2U] != -4.0) return false;
|
||||
}
|
||||
return true;
|
||||
};
|
||||
auto first = std::async(std::launch::async, [&] { return evaluate(moved); });
|
||||
auto second = std::async(std::launch::async, [&] { return evaluate(moved); });
|
||||
EXPECT_TRUE(first.get());
|
||||
EXPECT_TRUE(second.get());
|
||||
EXPECT_TRUE(evaluate(original));
|
||||
auto replacement = SparseMatrix::FromCoo(
|
||||
1U, 1U, {{0U, 0U, 7.0, 0U, 0U}}, {{0U, 1U}, {0U}});
|
||||
ASSERT_TRUE(replacement.HasValue());
|
||||
moved = replacement.Value();
|
||||
EXPECT_DOUBLE_EQ(moved.Multiply(Vector{1U, 3.0})[0U], 21.0);
|
||||
EXPECT_TRUE(evaluate(original));
|
||||
}
|
||||
|
||||
TEST(SparseAssembly, PreservesZeroShapesAndEmptyRows) {
|
||||
auto no_rows = SparseMatrix::FromCoo(0U, 3U, {}, {{0U}, {}});
|
||||
auto no_columns = SparseMatrix::FromCoo(2U, 0U, {}, {{0U, 0U, 0U}, {}});
|
||||
auto no_entries = SparseMatrix::FromCoo(2U, 3U, {}, {{0U, 0U, 0U}, {}});
|
||||
ASSERT_TRUE(no_rows.HasValue());
|
||||
ASSERT_TRUE(no_columns.HasValue());
|
||||
ASSERT_TRUE(no_entries.HasValue());
|
||||
EXPECT_EQ(no_rows.Value().Multiply(Vector{3U}).Size(), 0U);
|
||||
const auto empty_columns = no_columns.Value().Multiply(Vector{0U});
|
||||
const auto empty_entries = no_entries.Value().Multiply(Vector{3U});
|
||||
ASSERT_EQ(empty_columns.Size(), 2U);
|
||||
ASSERT_EQ(empty_entries.Size(), 2U);
|
||||
for (std::size_t row = 0; row < 2U; ++row) {
|
||||
EXPECT_DOUBLE_EQ(empty_columns[row], 0.0);
|
||||
EXPECT_DOUBLE_EQ(empty_entries[row], 0.0);
|
||||
}
|
||||
}
|
||||
|
||||
TEST(SparseAssembly, RejectsNonfiniteRhsAndRecoversAfterFiniteOverflow) {
|
||||
auto matrix = SparseMatrix::FromCoo(
|
||||
2U, 2U, {{0U, 0U, 2.0, 0U, 0U}}, {{0U, 1U, 2U}, {0U, 1U}});
|
||||
ASSERT_TRUE(matrix.HasValue());
|
||||
Vector rhs{2U, (std::numeric_limits<double>::infinity)()};
|
||||
EXPECT_THROW(static_cast<void>(matrix.Value().Multiply(rhs)),
|
||||
std::invalid_argument);
|
||||
rhs[1U] = 4.0;
|
||||
rhs[0U] = (std::numeric_limits<double>::max)();
|
||||
EXPECT_TRUE(std::isinf(matrix.Value().Multiply(rhs)[0U]));
|
||||
rhs[0U] = (std::numeric_limits<double>::quiet_NaN)();
|
||||
EXPECT_THROW(static_cast<void>(matrix.Value().Multiply(rhs)),
|
||||
std::invalid_argument);
|
||||
EXPECT_THROW(static_cast<void>(matrix.Value().Multiply(Vector{1U})),
|
||||
std::invalid_argument);
|
||||
rhs[0U] = 3.0;
|
||||
rhs[1U] = 4.0;
|
||||
const auto finite = matrix.Value().Multiply(rhs);
|
||||
EXPECT_DOUBLE_EQ(finite[0U], 6.0);
|
||||
EXPECT_DOUBLE_EQ(finite[1U], 0.0);
|
||||
}
|
||||
|
||||
TEST(SparseAssembly, MatchesIndependentLongDoubleResidualOnUnevenRows) {
|
||||
const std::vector<double> entries{1.25, -0.375, 4.5, -3.0, 0.125, 2.0};
|
||||
const SparsePattern pattern{{0U, 3U, 3U, 5U, 6U}, {0U, 2U, 4U, 1U, 3U, 2U}};
|
||||
std::vector<CooContribution> contributions;
|
||||
for (std::size_t row = 0; row < 4U; ++row) {
|
||||
for (auto position = pattern.row_offsets[row];
|
||||
position < pattern.row_offsets[row + 1U]; ++position) {
|
||||
contributions.push_back(
|
||||
{row, pattern.column_indices[position], entries[position], row,
|
||||
position});
|
||||
}
|
||||
}
|
||||
auto matrix = SparseMatrix::FromCoo(4U, 5U, contributions, pattern);
|
||||
ASSERT_TRUE(matrix.HasValue());
|
||||
Vector rhs{5U};
|
||||
for (std::size_t column = 0; column < 5U; ++column) {
|
||||
rhs[column] = 0.3 + static_cast<double>(column) * 0.7;
|
||||
}
|
||||
const auto product = matrix.Value().Multiply(rhs);
|
||||
for (std::size_t row = 0; row < 4U; ++row) {
|
||||
long double expected = 0;
|
||||
for (auto position = pattern.row_offsets[row];
|
||||
position < pattern.row_offsets[row + 1U]; ++position) {
|
||||
expected += static_cast<long double>(entries[position]) *
|
||||
rhs[pattern.column_indices[position]];
|
||||
}
|
||||
EXPECT_NEAR(product[row], static_cast<double>(expected), 2.0e-14);
|
||||
}
|
||||
}
|
||||
|
||||
} // namespace
|
||||
|
||||
@@ -6,6 +6,7 @@
|
||||
#include <filesystem>
|
||||
#include <limits>
|
||||
#include <memory>
|
||||
#include <optional>
|
||||
#include <stdexcept>
|
||||
#include <string>
|
||||
#include <utility>
|
||||
@@ -353,6 +354,41 @@ TEST(ResultRecoveryComponents,
|
||||
}
|
||||
}
|
||||
|
||||
TEST(ResultRecoveryComponents, PartitionedScaleKeepsCancelledInternalTerms) {
|
||||
auto definition = MakeShellDefinition();
|
||||
definition.node_sets = {{"Fixed", std::optional<std::string>{"Shell-1"},
|
||||
{0U}, {definition.source_path, 60U}}};
|
||||
definition.steps[0].boundaries = {
|
||||
{"Fixed", 1, 1, 1.0, {definition.source_path, 61U}}};
|
||||
const auto fixture = MakeShellFixture(std::move(definition));
|
||||
const auto count = fixture.dofs->FullDofCount();
|
||||
fesa::SparsePattern pattern;
|
||||
pattern.row_offsets = {0U, 1U, 3U};
|
||||
pattern.row_offsets.resize(count + 1U, 3U);
|
||||
pattern.column_indices = {0U, 0U, 1U};
|
||||
auto matrix = fesa::SparseMatrix::FromCoo(
|
||||
count, count,
|
||||
{{0U, 0U, 1.0, 0U, 0U}, {1U, 0U, -1.0, 0U, 1U},
|
||||
{1U, 1U, 1.0, 0U, 2U}}, pattern);
|
||||
ASSERT_TRUE(matrix.HasValue());
|
||||
fesa::Vector displacement{count};
|
||||
displacement[0U] = 1.0;
|
||||
displacement[1U] = 1.0;
|
||||
fesa::Vector external{count};
|
||||
external[1U] = 1.0e-12;
|
||||
const auto result = fesa::results_internal::GlobalEquilibriumRecovery(
|
||||
*fixture.domain, *fixture.dofs, matrix.Value(), displacement, external);
|
||||
ASSERT_TRUE(result.HasValue());
|
||||
EXPECT_DOUBLE_EQ(result.Value().internal_force[1U], 0.0);
|
||||
EXPECT_DOUBLE_EQ(result.Value().normalized_free_residual, 1.0e-12);
|
||||
displacement[1U] = std::numeric_limits<double>::quiet_NaN();
|
||||
const auto rejected = fesa::results_internal::GlobalEquilibriumRecovery(
|
||||
*fixture.domain, *fixture.dofs, matrix.Value(), displacement, external);
|
||||
ASSERT_FALSE(rejected.HasValue());
|
||||
ExpectStatusCode(rejected.GetStatus(), "nonfinite-recovery-value");
|
||||
EXPECT_DOUBLE_EQ(result.Value().reaction[1U], -1.0e-12);
|
||||
}
|
||||
|
||||
// C-MODULE-002
|
||||
TEST(ResultRecoveryComponents,
|
||||
BeamResultRecoveryKeepsEndpointGaussAndStressIdentities) {
|
||||
|
||||
@@ -3,6 +3,7 @@
|
||||
#include <gtest/gtest.h>
|
||||
|
||||
#include <cmath>
|
||||
#include <future>
|
||||
#include <initializer_list>
|
||||
#include <limits>
|
||||
#include <string>
|
||||
@@ -11,6 +12,7 @@
|
||||
|
||||
#include "fesa/fem/dof_manager.h"
|
||||
#include "fesa/math/sparse_matrix.h"
|
||||
#include "math/dense_blas_internal.h"
|
||||
|
||||
namespace {
|
||||
|
||||
@@ -123,6 +125,42 @@ TEST(MklPardisoSolver, ReusesOneFactorizationForRepeatedRhs) {
|
||||
EXPECT_LE(NormalizedResidual(matrix, second, rhs_second), 1.0e-10);
|
||||
}
|
||||
|
||||
TEST(MklPardisoSolver, SingleEquationPolicyPreservesLifecycleAndConcurrentTls) {
|
||||
const auto worker = [] {
|
||||
const int previous = mkl_set_num_threads_local(0);
|
||||
struct Restore {
|
||||
int previous;
|
||||
~Restore() { static_cast<void>(mkl_set_num_threads_local(previous)); }
|
||||
} restore{previous};
|
||||
const int default_threads = mkl_get_max_threads();
|
||||
fesa::MklPardisoSolver solver;
|
||||
for (int repeat = 0; repeat < 10; ++repeat) {
|
||||
if (!solver.Factorize(MakeDenseCsr(1U, {2.0})).IsOk()) return false;
|
||||
auto solution = MakeVector({9.0});
|
||||
if (!solver.Solve(MakeVector({4.0}), solution).IsOk() ||
|
||||
solution[0U] != 2.0) return false;
|
||||
if (!solver.Factorize(MakeDenseCsr(1U, {4.0})).IsOk()) return false;
|
||||
if (!solver.Solve(MakeVector({4.0}), solution).IsOk() ||
|
||||
solution[0U] != 1.0) return false;
|
||||
auto invalid_rhs = MakeVector({std::numeric_limits<double>::quiet_NaN()});
|
||||
if (solver.Solve(invalid_rhs, solution).IsOk() || solution[0U] != 1.0)
|
||||
return false;
|
||||
if (!solver.Solve(MakeVector({8.0}), solution).IsOk() ||
|
||||
solution[0U] != 2.0) return false;
|
||||
if (solver.Factorize(MakeDenseCsr(1U, {-1.0})).IsOk()) return false;
|
||||
if (solver.Solve(MakeVector({8.0}), solution).IsOk() ||
|
||||
solution[0U] != 2.0) return false;
|
||||
if (mkl_get_max_threads() != default_threads ||
|
||||
mkl_set_num_threads_local(0) != 0) return false;
|
||||
}
|
||||
return true;
|
||||
};
|
||||
auto first = std::async(std::launch::async, worker);
|
||||
auto second = std::async(std::launch::async, worker);
|
||||
EXPECT_TRUE(first.get());
|
||||
EXPECT_TRUE(second.get());
|
||||
}
|
||||
|
||||
TEST(MklPardisoSolver, StillRejectsNonsymmetricPublicCsr) {
|
||||
const auto nonsymmetric = MakeDenseCsr(2U, {2.0, 1.0, 0.0, 3.0});
|
||||
fesa::MklPardisoSolver solver;
|
||||
@@ -155,6 +193,32 @@ TEST(MklPardisoSolver, RefactorizesWithoutLeakingState) {
|
||||
1.0e-10);
|
||||
}
|
||||
|
||||
TEST(MklPardisoSolver, SingleEquationScopeTransitionsBetweenRetainedSizes) {
|
||||
const int previous = mkl_set_num_threads_local(0);
|
||||
struct Restore {
|
||||
int previous;
|
||||
~Restore() { static_cast<void>(mkl_set_num_threads_local(previous)); }
|
||||
} restore{previous};
|
||||
const int default_threads = mkl_get_max_threads();
|
||||
fesa::MklPardisoSolver solver;
|
||||
ASSERT_TRUE(solver.Factorize(MakeDenseCsr(1U, {2.0})).IsOk());
|
||||
auto single = MakeVector({0.0});
|
||||
ASSERT_TRUE(solver.Solve(MakeVector({4.0}), single).IsOk());
|
||||
EXPECT_DOUBLE_EQ(single[0U], 2.0);
|
||||
ASSERT_TRUE(solver.Factorize(MakeDenseCsr(2U, {2, 0, 0, 3})).IsOk());
|
||||
fesa::Vector pair{2U};
|
||||
ASSERT_TRUE(solver.Solve(MakeVector({4, 6}), pair).IsOk());
|
||||
EXPECT_NEAR(pair[0U], 2, 1e-14);
|
||||
EXPECT_NEAR(pair[1U], 2, 1e-14);
|
||||
EXPECT_EQ(mkl_get_max_threads(), default_threads);
|
||||
EXPECT_EQ(mkl_set_num_threads_local(0), 0);
|
||||
ASSERT_TRUE(solver.Factorize(MakeDenseCsr(1U, {4.0})).IsOk());
|
||||
ASSERT_TRUE(solver.Solve(MakeVector({8.0}), single).IsOk());
|
||||
EXPECT_DOUBLE_EQ(single[0U], 2.0);
|
||||
EXPECT_EQ(mkl_get_max_threads(), default_threads);
|
||||
EXPECT_EQ(mkl_set_num_threads_local(0), 0);
|
||||
}
|
||||
|
||||
TEST(MklPardisoSolver, ClassifiesSingularIndefiniteAndNonfiniteFailures) {
|
||||
fesa::MklPardisoSolver solver;
|
||||
|
||||
|
||||
@@ -3,6 +3,7 @@
|
||||
#include <gtest/gtest.h>
|
||||
|
||||
#include <cstddef>
|
||||
#include <future>
|
||||
#include <initializer_list>
|
||||
#include <limits>
|
||||
#include <type_traits>
|
||||
@@ -13,6 +14,7 @@
|
||||
#include "fesa/math/sparse_matrix.h"
|
||||
#include "fesa/math/vector.h"
|
||||
#include "fesa/solvers/linear/tangent_solver.h"
|
||||
#include "math/dense_blas_internal.h"
|
||||
|
||||
namespace {
|
||||
|
||||
@@ -129,4 +131,104 @@ TEST(TangentSolver, RejectsSolveBeforeSuccessfulFactorization) {
|
||||
EXPECT_DOUBLE_EQ(correction[1U], -9.0);
|
||||
}
|
||||
|
||||
TEST(TangentSolver, ReusesRhsButFreshValuesAndFailureCannotReuseStaleState) {
|
||||
fesa::MklPardisoTangentSolver solver;
|
||||
ASSERT_TRUE(solver.FactorizeFresh(MakeDenseCsr(2U, {2.0, 1.0, 0.0, 3.0}))
|
||||
.IsOk());
|
||||
fesa::Vector correction{2U};
|
||||
for (double scale : {1.0, -2.0, 0.5}) {
|
||||
ASSERT_TRUE(solver.SolveCorrection(MakeVector({4.0 * scale, 6.0 * scale}),
|
||||
correction).IsOk());
|
||||
EXPECT_NEAR(correction[0U], scale, 1.0e-14);
|
||||
EXPECT_NEAR(correction[1U], 2.0 * scale, 1.0e-14);
|
||||
}
|
||||
const auto bad_rhs = MakeVector({std::numeric_limits<double>::quiet_NaN(), 0});
|
||||
correction = MakeVector({17, -4});
|
||||
EXPECT_FALSE(solver.SolveCorrection(bad_rhs, correction).IsOk());
|
||||
EXPECT_DOUBLE_EQ(correction[0U], 17);
|
||||
EXPECT_DOUBLE_EQ(correction[1U], -4);
|
||||
ASSERT_TRUE(solver.SolveCorrection(MakeVector({4, 6}), correction).IsOk());
|
||||
ASSERT_TRUE(solver.FactorizeFresh(MakeDenseCsr(2U, {4, 0, 1, 2})).IsOk());
|
||||
ASSERT_TRUE(solver.SolveCorrection(MakeVector({4, 5}), correction).IsOk());
|
||||
EXPECT_NEAR(correction[0U], 1, 1.0e-14);
|
||||
EXPECT_NEAR(correction[1U], 2, 1.0e-14);
|
||||
auto diagonal = fesa::SparseMatrix::FromCoo(
|
||||
2U, 2U, {{0U, 0U, 5, 0U, 0U}, {1U, 1U, 7, 1U, 0U}},
|
||||
{{0U, 1U, 2U}, {0U, 1U}});
|
||||
ASSERT_TRUE(diagonal.HasValue());
|
||||
ASSERT_TRUE(solver.FactorizeFresh(diagonal.Value()).IsOk());
|
||||
ASSERT_TRUE(solver.SolveCorrection(MakeVector({10, -7}), correction).IsOk());
|
||||
EXPECT_NEAR(correction[0U], 2, 1.0e-14);
|
||||
EXPECT_NEAR(correction[1U], -1, 1.0e-14);
|
||||
EXPECT_FALSE(solver.FactorizeFresh(MakeDenseCsr(2U, {0, 0, 0, 0})).IsOk());
|
||||
correction = MakeVector({19, -8});
|
||||
const auto stale = solver.SolveCorrection(MakeVector({10, -7}), correction);
|
||||
ASSERT_FALSE(stale.IsOk());
|
||||
EXPECT_EQ(stale.Diagnostics().front().code, "solver-not-factorized");
|
||||
EXPECT_DOUBLE_EQ(correction[0U], 19);
|
||||
EXPECT_DOUBLE_EQ(correction[1U], -8);
|
||||
ASSERT_TRUE(solver.FactorizeFresh(diagonal.Value()).IsOk());
|
||||
EXPECT_TRUE(solver.SolveCorrection(MakeVector({10, -7}), correction).IsOk());
|
||||
}
|
||||
|
||||
TEST(TangentSolver, SingleEquationScopeRestoresTlsAcrossFreshFailureAndReuse) {
|
||||
const auto worker = [] {
|
||||
const int previous = mkl_set_num_threads_local(0);
|
||||
struct Restore {
|
||||
int previous;
|
||||
~Restore() { static_cast<void>(mkl_set_num_threads_local(previous)); }
|
||||
} restore{previous};
|
||||
const int default_threads = mkl_get_max_threads();
|
||||
fesa::MklPardisoTangentSolver solver;
|
||||
for (int repeat = 0; repeat < 10; ++repeat) {
|
||||
auto correction = MakeVector({17.0});
|
||||
if (!solver.FactorizeFresh(MakeDenseCsr(1U, {2.0})).IsOk()) return false;
|
||||
if (!solver.SolveCorrection(MakeVector({4.0}), correction).IsOk() ||
|
||||
correction[0U] != 2.0) return false;
|
||||
if (!solver.FactorizeFresh(MakeDenseCsr(1U, {4.0})).IsOk()) return false;
|
||||
if (!solver.SolveCorrection(MakeVector({4.0}), correction).IsOk() ||
|
||||
correction[0U] != 1.0) return false;
|
||||
if (solver.SolveCorrection(MakeVector({
|
||||
std::numeric_limits<double>::infinity()}), correction).IsOk() ||
|
||||
correction[0U] != 1.0) return false;
|
||||
if (solver.FactorizeFresh(MakeDenseCsr(1U, {0.0})).IsOk()) return false;
|
||||
if (solver.SolveCorrection(MakeVector({4.0}), correction).IsOk() ||
|
||||
correction[0U] != 1.0) return false;
|
||||
if (mkl_get_max_threads() != default_threads ||
|
||||
mkl_set_num_threads_local(0) != 0) return false;
|
||||
}
|
||||
return true;
|
||||
};
|
||||
auto first = std::async(std::launch::async, worker);
|
||||
auto second = std::async(std::launch::async, worker);
|
||||
EXPECT_TRUE(first.get());
|
||||
EXPECT_TRUE(second.get());
|
||||
}
|
||||
|
||||
TEST(TangentSolver, SingleEquationScopeTransitionsBetweenRetainedSizes) {
|
||||
const int previous = mkl_set_num_threads_local(0);
|
||||
struct Restore {
|
||||
int previous;
|
||||
~Restore() { static_cast<void>(mkl_set_num_threads_local(previous)); }
|
||||
} restore{previous};
|
||||
const int default_threads = mkl_get_max_threads();
|
||||
fesa::MklPardisoTangentSolver solver;
|
||||
ASSERT_TRUE(solver.FactorizeFresh(MakeDenseCsr(1U, {2.0})).IsOk());
|
||||
auto single = MakeVector({0.0});
|
||||
ASSERT_TRUE(solver.SolveCorrection(MakeVector({4.0}), single).IsOk());
|
||||
EXPECT_DOUBLE_EQ(single[0U], 2.0);
|
||||
ASSERT_TRUE(solver.FactorizeFresh(MakeDenseCsr(2U, {2, 1, 0, 3})).IsOk());
|
||||
fesa::Vector pair{2U};
|
||||
ASSERT_TRUE(solver.SolveCorrection(MakeVector({6, 6}), pair).IsOk());
|
||||
EXPECT_NEAR(pair[0U], 2, 1e-14);
|
||||
EXPECT_NEAR(pair[1U], 2, 1e-14);
|
||||
EXPECT_EQ(mkl_get_max_threads(), default_threads);
|
||||
EXPECT_EQ(mkl_set_num_threads_local(0), 0);
|
||||
ASSERT_TRUE(solver.FactorizeFresh(MakeDenseCsr(1U, {4.0})).IsOk());
|
||||
ASSERT_TRUE(solver.SolveCorrection(MakeVector({8.0}), single).IsOk());
|
||||
EXPECT_DOUBLE_EQ(single[0U], 2.0);
|
||||
EXPECT_EQ(mkl_get_max_threads(), default_threads);
|
||||
EXPECT_EQ(mkl_set_num_threads_local(0), 0);
|
||||
}
|
||||
|
||||
} // namespace
|
||||
|
||||
Reference in New Issue
Block a user